Available for Senior AI Architect Roles

Building the
Agentic AI
Future.

Som is having 17+ years of engineering · LangGraph & LangChain Architect · Designing production-grade autonomous systems that reason, route, and retrieve at scale.

17+
Years Engineering
3
Industry Domains
AWS
Solutions Architect
Agents Deployed
LangGraph LangChain FastAPI AstraDB Vector Search RAG Pipelines AWS ECS Fargate Multi-Agent Systems LoRA / QLoRA PEFT Fine-tuning CI/CD Python Docker LangGraph LangChain FastAPI AstraDB Vector Search RAG Pipelines AWS ECS Fargate Multi-Agent Systems LoRA / QLoRA PEFT Fine-tuning CI/CD Python Docker

Signature Projects

Production systems that move beyond demos — built for scale, reliability, and real-world deployment.

01
🕸️

LangGraph PDF & Web-Crawl Router Agent

A production-grade multi-node LangGraph graph with intelligent query routing between PDF vector retrieval and live DuckDuckGo web crawl. FastAPI backend, SHA-256 deduplication, AstraDB vector storage, and AWS ECS Fargate deployment pipeline.

LangGraph FastAPI AstraDB ECS Fargate
02
🧠

Agentic RAG with Adaptive Retrieval

A Retrieval-Augmented Generation pipeline with conditional edge routing and state machine logic — deciding dynamically between dense vector search, sparse keyword retrieval, and live web augmentation based on query confidence scoring.

RAG LangChain Vector DB Python
03

Fine-Tuning Pipeline: LoRA / QLoRA

End-to-end model fine-tuning using PEFT techniques (LoRA & QLoRA) targeting domain-specific tasks in Banking and E-Commerce. Efficient adapter training with quantization to run on constrained GPU infrastructure without quality loss.

LoRA QLoRA PEFT HuggingFace
04
🔗

API Gateway & Multi-Agent Orchestration

Kong / nginx API gateway integration for multi-agent FastAPI services — rate limiting, JWT validation, circuit breaking, and distributed tracing via OpenTelemetry. Designed to manage agent-to-agent communication in high-throughput environments.

Kong nginx JWT OpenTelemetry
05
🗃️

AstraDB Vector Knowledge Base

DataStax AstraDB-backed persistent knowledge store with configurable vector dimensions, keyspace partitioning, and real-time similarity search. Integrated with LangGraph state nodes for low-latency document retrieval across enterprise knowledge corpora.

AstraDB DataStax Embeddings LangGraph
06
🚀

CI/CD for AI Microservices (AWS)

GitLab CI/CD pipeline for containerised LangGraph FastAPI services — automated Docker builds, ECR pushes, ECS task definition updates, and rollback strategies. Includes environment-specific staging gates and integration test hooks.

GitLab CI AWS ECR ECS Docker

Core Stack

Every tool chosen for production readiness — not demo impressiveness.

🔷
LangGraph
Agentic Orchestration
⛓️
LangChain
Chain & Tool Framework
🐍
Python 3.12
Primary Language
FastAPI
API Backend
🗄️
AstraDB
Vector Store
☁️
AWS ECS
Container Orchestration
🐳
Docker
Containerisation
🔬
HuggingFace
Models & Fine-tuning
🔑
Kong / nginx
API Gateway
🔁
GitLab CI
CI/CD Pipeline
📊
OpenTelemetry
Observability
🧮
LoRA / QLoRA
Fine-tuning (PEFT)

Engineering Journey

2024 – Present
Agentic AI & LangGraph Architect · Publicis Sapient
Designing and delivering LangGraph-powered multi-agent systems, RAG pipelines, and AI-driven API platforms. Bridging enterprise consulting with cutting-edge generative AI architecture.
2018 – 2024
Senior Engineering & SDET Leadership
Led test automation frameworks (Selenium, Playwright, RestAssured, JMeter) and CI/CD pipelines across Banking, Retail, and IT Services verticals. Pioneered shift-left quality engineering practices at scale.
2012 – 2018
Full-Stack & Backend Engineering
Built Java/Spring-based microservices and backend systems for E-Commerce and Banking domains. Deep expertise in RESTful API design, distributed systems, and cloud migration.
B.Tech, Computer Science
RCC Institute of Information Technology, Kolkata
Foundation in algorithms, data structures, and systems design — applied across 17+ years of continuous engineering practice.

Ready to Architect
Your AI Future?

Open to senior Agentic AI Architect opportunities at MNCs and high-growth startups.
Let's discuss what intelligent systems can do for your organisation.