genai & agentic ai engineer

I architect agentic AI systems that ship to production. _

6+ years in software engineering, 2+ of them building and running large language model systems — multi-agent orchestration, retrieval-augmented generation, and LLM evaluation at scale.

base Python · LangGraph · LangChain · RAG · AWS Bedrock · Azure OpenAI  |  edu M.Tech AI, IIT Jodhpur

60%
lower LLM token cost
100+
production agents served
90%+
RAG retrieval accuracy
26%
lower median handling time
about

Building reliable AI systems, not demos

I'm a GenAI & Agentic AI Engineer with 6+ years of software engineering experience, including 2+ years designing and shipping production large language model systems. My focus is the part that's hard: making agents reliable, observable, and cost-efficient once they leave the notebook.

At NTT Data I architected a LangGraph multi-agent platform serving 100+ production agents, built hybrid RAG pipelines over 50K+ documents, and stood up an LLM evaluation and safety framework that catches regressions before they reach users. Before AI, I spent years as a full-stack engineer at Oracle and beyond — which is why my systems come with real APIs, tests, and CI/CD.

I'm currently pursuing an M.Tech in Artificial Intelligence at IIT Jodhpur, and I'm open to roles in Agentic AI, Generative AI, LLM, and AI/ML engineering.

skills

Technical stack

agentic ai

Multi-Agent SystemsAgent Orchestration ReActTool CallingMCPA2A

llm frameworks & platforms

LangChainLangGraphAWS Bedrock Azure OpenAIOpenAI APIVertex AICohere

rag & vector stores

RAGSemantic SearchEmbeddings Re-rankingQdrantpgvectorNeo4j

evaluation & observability

LangSmithLangfuseRagas DeepEvalLLM-as-JudgeNeMo GuardrailsBedrock Guardrails

languages & backend

PythonTypeScriptJavaScriptSQL FastAPIFlaskDjangoNode.jsgRPCWebSockets

data & cloud / devops

PostgreSQLRedisMongoDBDynamoDB DockerKubernetesGitHub ActionsCI/CDMLOps
experience

Where I've worked

Software Development Senior Specialist — NTT Data May 2024 — Present
  • Architected a production multi-agent platform on LangGraph with ReAct reasoning, intent routing, persistent DynamoDB memory and Redis caching — cutting median handling time 26% at 96%+ response quality.
  • Built a hybrid RAG pipeline over 50K+ documents using dense embeddings, semantic search, Cohere re-ranking and vector databases, reaching 90%+ retrieval accuracy.
  • Designed an LLM proxy microservice — a unified multi-model API (Bedrock + OpenAI) with fallbacks, prompt caching, auth, cost instrumentation and audit trails — cutting token costs 60% across 100+ agents.
  • Established an LLM evaluation & safety framework combining human-in-the-loop review, LLM-as-judge scoring, guardrails and centralized observability to catch regressions pre-deployment.

Python · LangGraph · LangChain · MCP · A2A · AWS Bedrock · FastAPI · DynamoDB · Redis · Docker · Kubernetes

Member of Technical Staff — Oracle Corporation Oct 2021 — May 2024
  • Integrated REST APIs and real-time clinical data pipelines into Cerner's EHR platform, enabling live patient-data retrieval across ML-assisted diagnostic workflows with 67% adoption across clinical teams.
  • Led platform-wide browser modernization (IE → Edge Chromium), cutting rendering time 85% and CPU usage 33%.
  • Built CI-integrated testing with React Testing Library, enabling teams to reach 100% critical-path coverage.
  • Awarded the Rising Star Award for delivering the Edge Chromium migration two months ahead of schedule.

React · TypeScript · JavaScript · REST APIs · Node.js · CI/CD

Software Engineer — J.P. Software Sep 2018 — Nov 2020
  • Engineered real-time chat and search with persistent history for high-traffic applications, lifting user engagement 10%.
  • Rebuilt the core transaction flow as a React + Node.js SPA (replacing a legacy multi-page app), cutting processing time 40% and improving retention 25%.
  • Created a Node.js production diagnostics module that improved stack-trace quality and cut debugging time for the team.

React · Node.js · JavaScript · REST APIs

projects

Selected work

01

Multi-Agent AI Platform

Production Agentic AI platform orchestrating 100+ agents with ReAct reasoning, intent routing, persistent memory, tool calling and quality-gated sub-task decomposition. Reduced median handling time 26% at 96%+ quality.

LangGraphPythonDynamoDBRedisMCP
02

Hybrid RAG Knowledge System

Retrieval-augmented generation over 50K+ documents with dense embeddings, semantic search and Cohere re-ranking against vector databases — 90%+ retrieval accuracy on internal evaluations.

RAGQdrantpgvectorCohereBedrock
03

LLM Proxy & Cost Optimizer

Unified multi-model API (AWS Bedrock + OpenAI) with automatic fallbacks, prompt caching, authentication, cost instrumentation and immutable audit trails. Cut token costs 60% across all agents.

FastAPIPythonAWS BedrockOpenAI API
04

LLM Evaluation & Safety Framework

End-to-end evaluation and observability with LLM-as-judge, rule-based validation, guardrails and human-in-the-loop review — surfacing regressions before deployment.

LangSmithLangfuseRagasDeepEvalNeMo Guardrails
education & certifications

Credentials

M.Tech — Artificial Intelligence

Indian Institute of Technology (IIT) Jodhpur · Dec 2024 — Dec 2026

B.Tech — Computer Science & Engineering

Shri Ramswaroop Memorial University · Aug 2013 — Jun 2017

Certifications

  • Microsoft Certified: Azure AI Engineer Associate
  • Oracle Cloud Infrastructure — Certified Generative AI Professional
contact

Let's build something intelligent.

Open to Agentic AI, Generative AI, LLM and AI/ML engineering roles. The fastest way to reach me is email or LinkedIn.