SRI HARSHA

System Architecture Architect  |  AI/Agentic Strategist  |  Telecom Systems
📞 +91 9880122928 ✉ reach.sriharsha@gmail.com 📍 Bengaluru, India 🏛 US Patent Holder
22+
Years Experience
3
Products to Market
3B
Events / Hour
1
US Patent
100x
Agentic Multiplier
Download Resume (PDF)

Professional Summary

22+ years building telecom and AI systems — from kernel-level packet processing to agentic AI platforms. Architect who has taken 3 products from R&D to commercial deployment, including the world's first commercial 3GPP Femto Gateway, the world's first 5G-NSA deployment at T-Mobile, and supporting Reliance Jio's greenfield all-IP LTE network.

Unique career arc spanning every layer of the technology stack: bare-metal C/C++ with DPDK, cloud-native Kubernetes microservices in Golang, and now full-stack AI/LLM/Agentic infrastructure. Expert at adopting open-source into enterprise solutions — accelerating development and cost optimization. Pioneered CI/CD, observability platforms, and test automation frameworks before industry standardization (pre-Jenkins, pre-Prometheus era).

Currently driving strategic AI adoption at Ribbon Communications: built on-premises LLM clusters (12 GPUs, 230GB VRAM), deployed RAG chatbots saving $100K+/year, engineered agentic RFx systems reducing sales response from months to days, and championing agentic software dark factories — where 16+ years of architecture experience — writing PRDs, FSDs, DSDs, and revision design specifications — now directly fuel autonomous code generation and software development at 100x velocity.

Career Timeline

2021 – Present
Ribbon Communications — System Architecture Architect, Research Labs
AI/Agentic strategy, 5G analytics (3B events/hr), on-prem LLM deployment, RAG systems, Acumen AI Platform, P4/eBPF research, VoNR analytics for Airtel India
2015 – 2021
Cisco Systems — Software Engineer IV
5G-NSA (T-Mobile world-first), Cloud-Native 5G SMF (QoS Modeling owner), MPTCP/DPDK prototype, SaMOG WiFi gateway, IEC-5 startup semifinalist
2014 – 2015
Samsung Research Institute — Chief Engineer
TAC lead for Reliance Jio — world's first/largest all-IP 4G/LTE network (125K gNB), EPC OAM for MME/SGW/PGW, managed team of 7
2008 – 2014
Nokia Solutions & Networks — Product Architect / OAM Expert
World's first commercial 3GPP Femto Gateway (SFR France), 60K APs at 99.999%, 120-member agile transformation, pioneered CI/CD + observability before industry standards, IMS CSCF cloud-native redesign with DPDK
2004 – 2008
Motorola India — Software Engineer
3G Flex/Feature Database for P2K platform, 172 simultaneous customers at Razr peak, automated workflows for 4X delivery, OTA updates, Advanced Flex Tool

Detailed Work Experience

Ribbon Communications — Research Labs
System Architecture Architect
2021 – Present (4+ years)
Ribbon Analytics Platform: Core architect on Ribbon's cloud-native, real-time big-data analytics platform. Architected systems processing 3 billion events/hour, serving 2.5M customers at Airtel India; designed to scale to 400 billion events/hour
5G VoNR Analytics: Enhanced Ribbon Analytics for full 5G stack (AMF, AUSF, SMF, gNodeB, UPF, PCF, UDM, CHF, NRF, NSSF, SCP); became quasi-NWDAF; first VoNR deployment at Airtel India
Acumen Platform: Key contributor to Ribbon's Acumen — an AIOps and automation platform for autonomous networking
Acumen AI Cluster: Built 5-node K8s cluster with 12 GPUs (8x L40S + 4x Tesla M60), 230 GB VRAM, 192 virtual GPU slices
Acumen AI Platform: Self-service platform (FastAPI + Celery + Flask + MCP Servers) on distributed Kubernetes infrastructure
RAG Chatbot: Pioneered on-premises LLM deployment; 100+ GB data, 10M+ tokens served, $100K+ annual savings
RFx Responder: Agentic AI system; reduced sales first response from months to days; accuracy improved 75% to 87%
LLM Fine-tuning: Built pipelines using Unsloth/LoRA/QLoRA/RLHF; created custom LLMs and SLMs
LLM Observability: Used Arize-Phoenix and Langfuse for tracing, evaluation, and dataset creation
Sentry Integration: Deployed Sentry for production issue tracking across products
MINT Project: Mobile Inband Telemetry using Intel Tofino switch with P4 programming — processing Terabits/second
MWC Demos (2022–Present): Delivered customer-facing POC demos at Mobile World Congress
CXO AI Strategy Advisory: Trusted advisor to VPs, SVPs, PMs, and CXOs on AI strategy
AI/ML Steering Committee: Key member driving enterprise GenAI adoption
PDF Chatbots: Implemented chatbot solutions across multiple product lines — $100K+ savings annually
Market Strategy: Competitive intelligence, product viability assessments, and MVP definition
XDR Creation: Passive monitoring of whole 5G network for eXtended Detection and Response records
LLMsRAGLoRA/QLoRARLHF LangChainLangGraphLlamaIndexLangflow vLLMOllamaHuggingFaceMCP Servers GolangPythonFastAPICelery KubernetesP4eBPF5G ClickHouseMilvusPrometheusGrafanaSentry Arize-PhoenixLangfuse
Cisco Systems India Pvt Ltd
Software Engineer IV — Mobility Unit
2015 – 2021 (6 years)
5G-NSA (T-Mobile): Architected 5G-NSA solution on MME/PGW for world's first 5G-NSA deployment
5G SMF (Cloud-Native): Owned QoS Modeling — the heart of Cisco's industry-first Cloud Native Standalone 5G Core
MPTCP Prototype: Prototyped cutting-edge Multipath TCP on DPDK for high-throughput networking
SaMOG WiFi Gateway: Designed and implemented S2a WiFi Offload features
Call Flow Diagram Tool: Built sequence diagram generation from distributed K8s pods
IEC-5 Startup: 5G-SPACE venture — semifinalist among 400+ submissions (top 20)
C/C++GolangPython gRPCProtobufDPDK KubernetesMicroservices5G Core
Samsung Research Institute, Bangalore
Chief Engineer
2014 – 2015 (1+ year)
Reliance Jio: Led TAC team supporting world's first and largest all-IP 4G/LTE network — 125K gNodeBs
EPC Operations: OAM of MME, SGW, PGW; managed KPIs for 100,000+ eNodeBs
Team Leadership: Managed team of 7 engineers
Customer Interface: Handled day-to-day operational issues
LTE/4GEPC CoreMMESGW/PGWOAM
Nokia Solutions & Networks
Product Architect / OAM Expert
2008 – 2014 (6 years)
World's First Femto Gateway: Architected world's first commercial 3GPP Femto Gateway (HNbGW) for SFR, France
FCAPS @ Scale: 60,000 concurrent Femto APs with 99.999% availability
Agile Transformation: Led transformation of 120-member cross-functional team
CI/CD Pioneer: Handcrafted CI/CD system before Jenkins existed; 5,000+ test cases in 3 hours
Health Monitor Console: Observability platform predating Prometheus/Grafana
IMS CSCF Redesign: Cloud-native using DPDK; 400% efficiency improvement
C/C++PerlPHP DPDKMySQLSNMPNETCONF/YANG
Motorola India Pvt Ltd
Software Engineer
2004 – 2008 (4 years)
3G Flex & Feature Database: Core developer for P2K phone platform across 5 continents
Scaling Achievement: 172 simultaneous customers at peak of Razr phones — 6X customer scaling
OTA Updates: Architected Over-The-Air update system for 3G phones
Advanced Flex Tool: Built standalone verification tool deployed across organization
C/C++VC++PerlSolarisMySQL3G/UMTS

Complete Technical Skills Inventory

AI / ML / Agentic Programming

LLMsSLMsRAG LoRAQLoRARLHFUnsloth vLLMOllama LangChainLangGraphLlamaIndexLangflow HuggingFacePyTorchOpenAI API Claude CodeGitHub CopilotWindsurfCursor Fine-tuning PipelinesPrompt Engineering MCP ServersAgentic WorkflowsReAct Patterns Context EngineeringTTS/STT Models

Telecom & Networking (3G/4G/5G)

5G Core (SMF, AMF, UPF, PCF, AUSF, UDM, CHF, NRF, NSSF, SCP) 4G/LTE (MME, SGW, PGW)3G/UMTS VoLTEVoNRIMS (HSS, CSCF, DRA) Femto Gateway (HNbGW)SaMOGNWDAF FCAPSOAM3GPP Specifications

Programming Languages

C (20+ years)C++ (20+ years) Python (10+ years)Golang (8+ years) Perl (15+ years)Shell Scripting JavaScriptPHP

Protocols & Standards (40+)

IP/IPv4/IPv6TCP/UDPGTPv2 RADIUSDiameterEAP-SIM/AKA IPSec/IKEv2gRPC/Protobuf SNMPNETCONF/YANGSIPMPTCP TR-069/TR-181/TR-196GRE/EoGRE/PMIP

Cloud & Infrastructure

KubernetesDockerMicroservices AWS BedrockGCPAzure High-Availability (99.999%)

Systems & Performance

DPDKP4 Programming (Intel Tofino) eBPFMulti-core Programming UNIX/Linux InternalsReal-time Packet Processing

Data & Databases

ClickHouseHadoopParquet Milvus (Vector DB)Redis PostgreSQLMySQL

Observability & Monitoring

PrometheusGrafana Arize-PhoenixLangfuse SentryOpenTracing

Frameworks & Full-Stack

FastAPIFlaskCelery ReactREST APIsSOAP

Product & Leadership

Product Lifecycle (Concept to Market) PRD / FSD / DSD Authoring MVP Definition Agile Transformation (120 members) Scrum Master Cross-functional Team Leadership
Technology Stack — Mapped Like an Operating System

From user-space AI applications down to bare-metal hardware — 22 years of expertise at every layer

AI / Agentic
User Space
LLMsRAGLoRA/QLoRA LangChainLangflowvLLM OllamaClaude CodeMCP Servers
Application
Layer
FastAPIFlaskReact CeleryREST APIsgRPC/Protobuf
Orchestration
& Platform
KubernetesDocker CI/CDPrometheusGrafana SentryGPU Orchestration
Service &
Telecom Core
5G SMF/AMF/UPF4G MME/SGW/PGW IMS CSCF/HSSFemto Gateway VoLTEVoNR
Network &
Protocol Stack
TCP/IP/UDPGTPv2RADIUS/Diameter IPSec/IKEv2MPTCPSIP SNMPNETCONF/YANG
Data Plane &
Kernel Space
DPDKeBPF P4 (Intel Tofino)Linux Internals Multi-core Programming
Hardware &
GPU Infra
NVIDIA A100H100L40S Tesla M60Intel Tofino 12-GPU Cluster (230GB VRAM)
Core Capabilities — Inner Core to Outer Core
C/C++ (20 yr) DPDK Linux Internals Multi-core / Threads System Architecture Product Vision Kubernetes / Docker 5G Core (SMF/AMF/UPF) 4G/LTE (MME/PGW) CI/CD Pioneer IMS (CSCF/HSS) Cloud-Native Microservices gRPC/Protobuf 3GPP/IETF LLM Fine-tuning (LoRA / QLoRA / RLHF) RAG Systems (100+GB) LangChain / LangGraph MCP Servers Agentic Workflows Prompt Engineering ML Ops / Observability Langflow / LlamaIndex Claude Code / Copilot vLLM / Ollama / HuggingFace On-Prem GPU (12 GPUs, 230GB VRAM) Voice Agents / TTS / STT Systems DNA (20yr) Cloud & Telecom AI / Agentic

Why 16+ Years of Architecture & Spec-Writing Enables 100x in Agentic Software Dark Factories

In the emerging world of agentic software development, the bottleneck is no longer coding — it's precise specification. AI agents can generate code at machine speed, but only if they receive unambiguous, architecturally-sound specifications.

With 16+ years of architecture experience — writing PRDs, FSDs, DSDs, and Revision Design Specifications across Nokia, Samsung, Cisco, and Ribbon — I have internalized the discipline of converting business intent into precise, implementable technical specifications. This is the exact skill that transforms agentic tools from 2x helpers into 100x multipliers.

My unique advantage: I don't just write specs — I have deployed the agentic tools across an entire organization, fine-tuned LLMs on product-specific domain knowledge, and built the MCP server infrastructure. I represent the rare combination of specification author + agentic infrastructure builder + systems architect.

The 100x Multiplier Stack

1. Specification Precision = Agent Accuracy

16+ years of writing 3GPP-compliant specs means I produce specifications with the precision that AI agents need. Ambiguity kills agent performance — my specs eliminate it.

2. Full-Stack Architecture = Complete Agent Context

From DPDK kernel-level code to Kubernetes orchestration to LLM fine-tuning — I understand every layer an agent might touch.

3. Agentic Infrastructure Builder

Built Acumen AI Platform (FastAPI + Celery + MCP Servers) as the backbone for agentic workflows. Deployed Langflow for low-code agent orchestration.

4. LLM Fine-tuning on Domain Knowledge

Fine-tuned LLMs using LoRA/QLoRA/RLHF on product-specific knowledge. Built RAG systems over 100GB+ of domain documentation.

5. Enterprise-Scale AI Deployment

Built and operated a 12-GPU, 230GB VRAM AI cluster. Introduced agentic coding tools across multiple teams.

6. Pioneer Mentality

Built CI/CD before Jenkins. Built observability before Prometheus. Now building agentic software factories before they're mainstream.

The Dark Factory Vision

A software dark factory is a development pipeline where AI agents autonomously generate, test, deploy, and monitor code. My career has been a perfect preparation for this: 16+ years of writing machine-readable specifications, building CI/CD and observability infrastructure, and now deploying the AI/LLM infrastructure that powers the agents themselves. The result: 100x the output of traditional development.

Key Projects & Initiatives

Ribbon Analytics — 5G Event Processing

Ribbon Communications | 2021–Present

Architected analytics pipeline processing 3B events/hour, serving 2.5M customers at Airtel India. Full 5G stack support. Designed to scale to 400B events/hour.

3B events/hour → 400B target

Acumen AI Cluster & Platform

Ribbon Communications | 2023–Present

5-node K8s cluster with 12 GPUs, 230GB VRAM, 192 virtual GPU slices. Self-service AI platform — a scaled-down Amazon Bedrock equivalent.

12 GPUs | 230GB VRAM | 192 vGPU

RAG Chatbot — On-Prem LLM

Ribbon Communications | 2023–Present

On-premises LLM deployment. 100+ GB knowledge base, 10M+ tokens served, $100K+ annual savings with full data sovereignty.

$100K+ annual savings | 10M+ tokens

RFx Responder — Agentic AI

Ribbon Communications | 2024–Present

Agentic AI handling 15,000 technical questions in minutes. Reduced sales first response from months to days. Accuracy: 75% to 87%.

Months → Days | 75% → 87%

MINT — Mobile Inband Telemetry

Ribbon Communications | 2022–Present

Process Terabits/second using Intel Tofino switch with P4 programming. Metadata creation for ML-based network analysis.

Terabits/second processing

Cisco 5G-NSA — T-Mobile

Cisco Systems | 2018–2019

Architected 5G-NSA solution for world's first 5G-NSA deployment at T-Mobile.

World's First 5G-NSA Deployment

Cisco 5G SMF — Cloud-Native Core

Cisco Systems | 2018–2021

Cisco's industry-first Cloud Native Standalone 5G Core. Owned QoS Modeling (heart of SMF).

Industry-First Cloud-Native 5G Core

Femto Gateway (HNbGW) — World's First

Nokia Solutions & Networks | 2008–2014

World's first commercial 3GPP Femto Gateway for SFR, France. 60,000 APs with 99.999% availability.

World's First | 60K APs | 99.999%

Reliance Jio LTE Network

Samsung Research | 2014–2015

TAC lead for world's first all-IP 4G/LTE network — 125K gNodeBs. KPIs for 100,000+ eNodeBs.

World's Largest All-IP LTE Network

IEC-5 Startup — 5G-SPACE

Cisco Systems | 2019

Semifinalist among 400+ submissions (top 20) in Cisco CTO organization.

Top 20 of 400+ submissions

Strategic Leadership & AI Advisory

Beyond hands-on engineering, I serve as a trusted AI strategy advisor to senior leadership — helping VPs, SVPs, Product Managers, and CXOs gain clarity on AI strategy, investment decisions, and technology roadmaps.

MWC POC Demos (2022–Present)

Delivered customer-facing POC demos at Mobile World Congress — AI-powered analytics, agentic AI platforms, and network intelligence showcases.

CXO AI Strategy Advisory

Consulted by CXOs, SVPs, and VPs to translate complex GenAI/LLM concepts into actionable business strategies. Build vs. buy decisions, investment prioritization.

Executive Presentations

Prepared AI strategy presentations, technology roadmap slides, and competitive analysis decks for senior leadership.

AI/ML Steering Committee

Core member driving enterprise GenAI adoption. Introduced developer tools (Codeium, Windsurf, Cursor, Copilot), moderated internal AI/ML forum.

Product Manager AI Enablement

Guided PMs on integrating AI capabilities into product roadmaps — identifying features that benefit from LLMs, RAG, fine-tuning, or agentic workflows.

Market Analysis & Competitive Intelligence

Conducted product viability assessments, MVP definition, and competitive intelligence for next-gen analytics and AI products.

Strategic Impact

The ability to bridge deep technical expertise with strategic business communication differentiates an architect from a technology leader. From MWC demos that win customer interest to slides that give CXOs clarity on multi-million dollar AI investments — this strategic advisory role amplifies the impact of every technical capability.

AI Lab & Hands-on Experimentation

Active personal AI experimentation lab — a living cookbook of hands-on projects exploring cutting-edge AI/ML techniques. Each experiment is designed to deeply understand underlying mechanisms.

Voice Agent with LiveKit + Sarvam AI

Real-time voice agent using LiveKit WebRTC, Sarvam STT/TTS, and local Gemma3:4B via Ollama. Complete pipeline: streaming audio → STT → LLM reasoning → TTS → voice response.

LiveKitSarvam AIGemma3WebRTC

Complete Unsloth Fine-tuning Lab

LoRA and QLoRA on Llama 3.2 3B with 4-bit quantization, PDF-to-QA data pipelines, GGUF export for Ollama, ROUGE/BERTScore evaluation.

UnslothLoRALlama 3.2GGUF

RFQ Compliance Assessment — RAG + LangChain

RAG-powered compliance system using DeepSeek-R1:8B, LangChain, Chroma. Multi-stage retrieval: cosine similarity → cross-encoder re-ranking → fuzzy matching.

DeepSeek-R1LangChainChromaRAG

Custom Langflow Components

Built custom Langflow components: KB List Fetcher, Ollama integration, regex processors, URL processors, and OpenAI wrappers.

LangflowCustom ComponentsPython

Go → Python Celery Integration

Golang-to-Celery bridge — Go as high-performance backend submitting async tasks to Python Celery workers via Redis.

GolangCeleryRedisPython

Firebase Auth + FastAPI RBAC

Role-based access control using Firebase Authentication with FastAPI — JWT verification, dependency injection, user DB management.

FirebaseFastAPIJWTRBAC

Complete Gen AI / LLM Masterclass

Full NLP/ML pipeline: Text Generation with TensorFlow/Keras/LSTM, summarization, POS tagging, classification, Text-to-Image with HuggingFace.

TensorFlowKerasLSTMHuggingFace

Excel RAG Processor

Intelligent Excel-to-vector-DB ingestion: logical table detection, structure-preserving markdown conversion, smart chunking respecting table boundaries.

RAG ChunkingVector DBPandas

Education

Master of Science — Software Systems

BITS, Pilani | 2009 – 2011
CGPA: 7.26

Bachelor of Engineering — Information Science & Engineering

AIT, Chickmagaluru / VTU, Belgaum | 2000 – 2004
76%

Pre-University (PUC)

DRM Science College, Davangere | 2000
76%

10th Standard (SSC)

Bapuji | 1998
73%

Patent

US011350319B2

Optimized Quality of Service Enforcement for Handover Between Different Radio Access Types

US Patent — Granted.

Certifications

Introduction to LangGraph

LangChain Academy | December 2025

Foundation: Introduction to LangChain — Python

LangChain Academy | December 2025

Agentic AI!

DeepLearning.AI | October 2025

Building AI Voice Agents for Production

DeepLearning.AI | September 2025

Advanced NLP Techniques: LoRA for Fine-Tuning Llama3

Udemy | February 2025

Machine Learning for Absolute Beginners

Udemy | February 2023

Awards & Recognition

US Patent Holder — QoS optimization for inter-RAT handover
IEC-5 Semifinalist — 5G-SPACE, top 20 of 400+ at Cisco
BU Innovation Finalist — Real Time Analyzer for Logs at Nokia
BU Innovation Finalist — Health Monitor Console at Nokia
Most Inspiring Person — Femto Gateway team at Nokia
Spot Award — FGW 1.0 features integration
Spot Award — CI framework development
Star Scrum Team Award — Team delivery at Nokia

Personal

Date of Birth: March 28, 1983

Languages: Kannada, English, Hindi

Interests: Technology exploration, photography, traveling, reading, music

Teaching, Training & Mentoring

Teaching and enabling others has been a steady part of the architect role across Nokia, Samsung, Cisco, and Ribbon — onboarding new engineers, running company-wide technical training, guiding university students through AI capstone projects, and helping engineering and sales teams reach working proficiency on new tools and agentic workflows, not just theoretical familiarity.

New Joiner Onboarding

Nokia  ·  Samsung  ·  Cisco  ·  Ribbon | Ongoing

Ongoing responsibility across every role — ramping new team members on codebase, architecture, 3GPP protocols, and debugging workflows through hands-on pairing until they are independently productive.

University Capstone Mentoring (AI Domain)

Indian & US Universities | Ongoing

Mentored graduate, post-graduate, and PhD students on AI capstone projects — scoping problem statements, guiding LLM/RAG/agent design choices, evaluation methodology, and reviewing final deliverables.

Agentic Workflow Enablement for Engineering

Ribbon Communications | 2023–Present

Helped engineering teams adopt agentic flows for log analysis and reasoning agents — walking through prompt design, tool wiring, memory and context patterns, and observability so teams can extend the agents themselves.

Company-wide Technical Training (Twice a Year)

Ribbon Communications | 2021–Present

Delivered in-person technical training sessions to audiences of up to 50 attendees — covering telecom architecture topics, AI/LLM fundamentals, and new platform capabilities.

On-Prem AI Hackathon Enablement

Ribbon Communications | 2023–Present

Company-wide responsibility for assessing participant readiness and training teams on on-prem AI infrastructure ahead of internal AI hackathons — cluster access, LLM and framework selection, agent tooling — so teams spend hackathon hours on ideas, not setup.

Architect-Led Enablement for Program & Sales

Ribbon Communications | 2021–Present

Partnered with program management and sales to scale up adoption of AI tools — translating technical detail into what engineering needs to execute, and distilling solution options into what sales needs to position confidently.

Agile & CI/CD as a Learning Exercise

Nokia Femto Gateway | 2010–2012

The move to agile and a handcrafted CI/CD toolchain was driven through hands-on training — building the tooling alongside the 120-member team so the new way of working became a working skill, not a slideware change.

The Teaching Philosophy

The distinction that runs through all of these engagements: the goal is always working proficiency, not theoretical familiarity. Whether onboarding a new graduate engineer at Nokia, training a sales team on AI positioning, or guiding a PhD student through RAG architecture choices — the measure of success is whether the person can operate independently afterward. The architect role is a force multiplier; so is teaching.