AI/ML Engineering Lead Product Management Developer Relations Open Source

Sanika Tungare

I build production agentic AI systems and lead 0→1 AI products that ship.

9+ years architecting multi-agent pipelines, enterprise RAG, and LLM platforms at scale. Led AI product strategy driving $2M+ ARR — from LangGraph cybersecurity agents processing 100K+ events to RAG serving 500+ users across 50K+ documents. I own the roadmap, build the systems, and ship what works.

9+
Years Production AI
$2M+
ARR Impact
100+
GitHub Repos
50K+
Developers Reached
Impact

Numbers that speak for themselves.

Quantified results from production AI deployments, product launches, and team leadership.

40%
Automation Gains
Efficiency improvement via multi-agent pipelines automating cybersecurity, invoicing, and defect triage.
60%
Work Reduction
Less analyst time on security triage — agentic pipeline processes 100K+ daily events autonomously.
95%
RAG Accuracy
Retrieval accuracy across 50K+ enterprise docs with hybrid search and semantic chunking. 3s avg response.
35%
Fewer Hallucinations
Reduced LLM hallucinations through hybrid search, context engineering, and advanced chunking.
$2M+
ARR Driven
Translated enterprise requirements into AI agent solutions — owned product roadmap and GTM execution.
Deploy Velocity
CI/CD pipelines, A/B frameworks, real-time monitoring on AWS/GCP. Deployment: 4h → 20min.
25+
AI Features Shipped
Enterprise LLM platform with GPT-4, Claude, and AWS Bedrock powering 25+ production features.
40%
User Adoption
Scaled AI products from concept to production — data-driven experimentation driving measurable growth.
Featured Projects

Production AI that solves real problems.

Each project ships to production with real trade-offs considered — not toy demos.

Agentic AICybersecurity

🛡️ LangGraph Cybersecurity Agent Pipeline

Security teams manually sifting through daily alerts — slow, error-prone, burning out analysts. Built multi-agent pipeline: cleaning → validation → enrichment → threat detection → reporting.

✦ 100K+ daily events · 92% accuracy · 60% analyst workload reduction

Trade-off: Higher infrastructure cost and pipeline complexity in exchange for speed and accuracy at scale.

LangGraphGPT-4FAISSPostgreSQLDockerKubernetes
→ View on GitHub
RAGEnterprise

🧠 Enterprise RAG Knowledge System

50K+ documents scattered across systems — employees couldn't find answers fast. Built production RAG with semantic chunking, hybrid search (dense + sparse), serving 500+ users.

✦ 95% retrieval accuracy · 3s avg response · 50K+ doc corpus

Trade-off: One-time embedding/indexing cost exchanged for eliminated manual retrieval and sub-second latency.

LangChainWeaviateCohereFastAPIRedisOpenAI API
→ View on GitHub
A2A ProtocolCloud-Native

🤝 Universal Commerce Protocol (UCP)

Commerce backends couldn't coordinate intelligently — every integration was hard-coded. Built protocol-first multi-agent system with A2A coordination, LLM reasoning, and human-in-the-loop safeguards.

✦ Zero hard-coded workflows · Real-time orchestration · Production interop

Trade-off: Protocol-first design adds complexity and LLM latency — with zero future integration costs and HIL production reliability.

Gemini APIA2A ProtocolsUCPREST APIsStructured Outputs
→ View on GitHub
ProductPlatform

🤖 AI Agent Platform for Enterprise

Every new AI agent was built from scratch — inconsistent, slow to ship, not reusable. Created scalable framework with pre-built tools, memory, and modular plug-and-play components.

✦ 20+ custom agents deployed · Finance, healthcare, logistics

Trade-off: AWS Bedrock vendor lock-in limits portability — but delivers scaling, security, and zero infra management.

LangChainAutoGenAWS BedrockDynamoDBLambda
→ View on GitHub
GraphRAGKnowledge Graph

🔗 GraphRAG + Neo4j + LangChain + Groq

Standard RAG loses relational context between documents. Combined vector search with graph traversal on Neo4j for multi-hop reasoning and knowledge discovery.

✦ Superior relational reasoning · Multi-hop queries · Graph + vector hybrid
Neo4jLangChainGroqGraph Traversal
→ View on GitHub
Invoice AIProduction

📄 cXML Invoice Processing Assistant

Manual invoice processing was slow and error-prone across 10K+ monthly documents. Built embedding-based search with automated classification and extraction.

✦ 10K+ monthly invoices · 95% accuracy · 80% time reduction
EmbeddingsVector SearchcXMLFastAPI
Voice AIAgent

🛒 Voice-Enabled Shopping Cart Agent

E-commerce needs natural language interfaces. Built voice-first AI agent with real-time STT/TTS, LLM reasoning, and agent orchestration for seamless shopping.

✦ Voice-first shopping · Natural language · Real-time orchestration
STT/TTSLLM APIsAgent Orchestration
→ View on GitHub
Medical AIGoogle Cloud

🩺 DermScreener AI — MedGemma

Dermatology screening needs scalable AI assistance. Built medical AI with MedGemma on Google Cloud for production screening — Kaggle competition entry.

✦ Medical AI on Google Cloud · MedGemma · Kaggle entry
MedGemmaGoogle CloudVertex AIKaggle
→ View on GitHub
AWS BedrockLangGraph

☁️ AWS Bedrock + LangGraph Studio + Claude

Production agents need visual workflow orchestration. Combined AWS Bedrock with LangGraph Studio for enterprise-grade agent deployment and management.

✦ Visual agent orchestration · Production-grade on AWS
AWS BedrockLangGraph StudioClaude
→ View on GitHub
Tech Stack

Built to ship at scale.

Production-tested across the full AI/ML stack — from model selection to deployment at scale.

LLMs & AI Frameworks

Models & Orchestration
GPT-4Claude 3.5GeminiMistralLangChainLangGraphAutoGenCrewAIOpenAI APIAnthropic API

Agentic AI

Multi-Agent Systems & Protocols
Multi-Agent OrchestrationReAct AgentsTool-Use / Function CallingAgent MemoryA2A ProtocolsMCP ServersHuman-in-the-Loop

RAG & Vector Databases

Retrieval, Search & Knowledge Graphs
FAISSWeaviatePineconeChromaDBQdrantHybrid SearchSemantic ChunkingCohere EmbeddingsNeo4j GraphRAGContext Engineering

ML Engineering

Training, Fine-Tuning & Evaluation
PyTorchTensorFlowScikit-learnHugging FaceLoRA / QLoRAA/B TestingLLM Evaluation

Cloud & MLOps

Infrastructure & Deployment
AWS SageMakerAWS BedrockGCP Vertex AIAzureDockerKubernetesMLflowAirflowCI/CD

Engineering

Backend, APIs & Data
PythonJavaFastAPIFlaskREST APIsKafkaStreamlitGitHub ActionsSQLMongoDBDynamoDB

Observability & Debugging

Monitoring & Evaluation
LangSmithGrafanaPrometheusETL PipelinesLLM Evaluation Frameworks

Product & Leadership

Strategy, GTM & Team Building
0→1 Product StrategyMulti-Year RoadmapsAPI StrategyCross-Functional LeadershipGTM ExecutionTechnical MentorshipData-Driven Experimentation
Experience

9+ years. Progressive growth. Deep impact.

From software engineer to AI/ML product lead — building systems that drive real business outcomes.

June 2023 — Present
AI Engineering & Product Management Lead
Corcentric — Cherry Hill, NJ
  • Architected production agentic AI with LangChain, LangGraph, AutoGen — 40% automation efficiency, 60% manual work reduction
  • Built enterprise LLM platform (GPT-4, Claude, AWS Bedrock) — enabled 25+ AI-powered features in production
  • Developed multi-modal RAG with FAISS + Weaviate — 45% improved retrieval, 35% fewer hallucinations
  • Owned 3-year multi-agent AI platform roadmap — translating ambiguous problems into scalable solutions
  • Defined API strategy and tool interfaces for modular agent architecture enabling extensibility across product lines
  • Scaled AI products from concept to production — 40% user adoption improvement through data-driven experimentation
  • Product strategy driving $2M+ ARR — owned roadmap, GTM execution, and cross-functional alignment
  • Mentored 8 engineers on LLM best practices and agent design — reduced onboarding time 40%
June 2021 — June 2023
Software Lead — AI/ML
Corcentric — Cherry Hill, NJ
  • Production multi-turn chatbot (GPT-3.5/4, Claude) — 92% user satisfaction, 85% query resolution
  • GPT-4 self-learning test generation framework integrated with Grafana — 70% less manual test authoring
  • LLM evaluation framework measuring accuracy, relevance, toxicity, hallucination rates — established baselines
  • Led cross-functional teams (Product, Eng, UX, Sales, Support) to deliver 15+ AI-driven features
  • Established automation frameworks and executive dashboards — $500K+ annual savings
June 2016 — June 2021
Software Engineer — Developer Relations
Corcentric — Cherry Hill, NJ
  • Created technical AI/ML content and tutorials — 35% developer adoption increase, 25% fewer support tickets
  • Built GitHub Actions CI/CD pipelines with quality gates — deployment time 4h → 20min
  • Deployed Grafana + Prometheus observability dashboards tracking quality metrics and system health
  • Performance engineering with JMeter — 40% response time improvement
Open Source

Building in public.

Creator and maintainer of open-source AI tools used by developers.

🐊 Crocy — Chrome Extension

AI-powered Chrome extension built on OpenAI. Every-page AI assistant bringing context-aware intelligence right into your browser — summarize, explain, translate, or query any web page.
→ View on GitHub

🔍 TraceContext AI

Open-source persistent AI coding context platform. Solves the #1 broken experience in AI-assisted development: every session ends, the AI loses all memory. TraceContext preserves architecture, decisions, and context.
→ View Organization
Repository Index

100+ repositories. All public.

Organized by category — agentic AI, RAG pipelines, cloud, ML, voice, and more.

View all 100+ repositories →
Developer Relations & Content

Building community at scale.

Technical content, conference talks, and hands-on workshops — sharing production AI knowledge.

25+
Blog Posts
Technical tutorials on LLMs, RAG, and Agentic AI reaching 50K+ developers.
5+
Conference Talks
Presented on LangChain, vector databases, and production LLM systems.
10+
Workshops Led
Teaching prompt engineering and agent development to founders and engineers.
SanikaGPT
AI Clone
Custom GPT answering questions about my work, projects, and expertise.
Credentials

Certifications

Google Cloud
GenAI Agents — 5-Day AI Agents Intensive
Google Cloud
Vertex AI Gemini API Skill Badge
Google Cloud
GenAI Apps with Gemini & Streamlit
Google Cloud
Explore Generative AI with Vertex AI
Google Cloud
GenAI: Beyond Chatbots
Kaggle
Hackathon & Competition Badges — AI/ML
Get In Touch

Let's build something extraordinary.

Open to AI/ML Engineering, Product Management, and Leadership roles at companies pushing the frontier.

saisanirose@gmail.com LinkedIn GitHub 🤖 SanikaGPT