Agentic AI Engineer

Akash
Chaudhari

LangGraph MCP Server Multi-Agent AutoGen · CrewAI RAG · GraphRAG LlamaIndex DeepEval · RAGAS LLM-as-Judge Azure · Databricks Kubernetes · FastAPI PydanticAI LLM Evaluation MS AI · IIT Patna
// agent_orchestration.live
About

Who I am

4+ years designing and deploying production AI across public sector and enterprise — systems that handle real users, real data, and real failures.

I build AI systems that actually ship. Over the past 4+ years I've designed and deployed production-grade Generative AI and Agentic AI systems — first for the Government of Maharashtra at scale, now at Deloitte South Asia LLP as an Assistant Manager.

My core work sits at the intersection of multi-agent orchestration, RAG architecture, and LLMOps. I've built LangGraph multi-agent systems with intent-classification routing, constructed MCP servers for standardised tool integration, implemented hybrid RAG with cross-encoder re-ranking, and shipped embedding-based knowledge retrieval grounding LLM responses in verified documentation.

I take evaluation seriously. Anyone can wire together a RAG pipeline — not everyone can tell you whether it's working. I build RAGAS + DeepEval evaluation harnesses, custom LLM-as-Judge evaluators, and CI/CD gates that block deployments when faithfulness drops below threshold.

My production stack spans Azure, Databricks, Kubernetes, FastAPI, and Docker — systems load-tested at 100 concurrent users with real p99 latency numbers documented. Currently pursuing an MS in AI & Cybersecurity at IIT Patna alongside full-time work at Deloitte.

0
Years Production AI
0
Enterprise Deployments
0
GitHub Projects
0
Certifications
Education
M.S. — AI & Cybersecurity
IIT Patna
Pursuing
B.E. — Automobile Engineering
University of Mumbai
2018
Certifications
Microsoft AI · Coursera
AI & ML Engineering
Mar 2025 · PTX8XBG3KH6K
IBM · Coursera
Generative AI for Data Scientists Specialization
Mar 2025 · M89N894KLOV2
Vanderbilt University · Coursera
AI Agents & Agentic AI with Python
Jun 2025 · 2MUKV1I2TQAP
IBM · Coursera
Fundamentals of AI Agents Using RAG & LangChain
Jun 2025 · KQCY9L3490ZP
Google Cloud · Coursera
Build & Deploy an Agent with Vertex AI Reasoning Engine
Jun 2025 · 6C7QLACT4SQJ
Microsoft AI · Coursera
Microsoft Azure for AI & Machine Learning
Mar 2025 · 9JF7X7ZM8W2T
Akash Chaudhari · Agentic AI Engineer · 2026Mumbai, India · Global Remote
Skills

Technical Stack

Production-verified across enterprise deployments and 6 portfolio projects — every skill has shipped code behind it.

Agentic AI & Orchestration
LangGraphLangChainMulti-Agent SystemsTool CallingFunction CallingHuman-in-the-LoopReActMCP Server BuildAutoGenCrewAI
Generative AI & RAG
RAG PipelinesHybrid SearchEmbeddingsSemantic SearchAzure OpenAIHugging FacePrompt EngineeringGuardrailsSelf-RAGCorrective RAGGraphRAGLlamaIndexCross-Encoder Re-ranking
Vector Databases
FAISSChromaPineconeWeaviate
LLM Engineering & Evaluation
Structured OutputsAI-assisted Code GenLangSmithDeepEvalRAGASLLM-as-JudgePydanticAICI/CD Eval GatesPrompt Versioning (MLflow)
Cloud, Infra & Deployment
Azure FunctionsAzure App ServiceAzure AI ServicesDatabricksMLflowDockerAzure DevOps CI/CDKubernetes / AKSFastAPI
Engineering Practices
PythonSQLREST APIsPytestLocust Load TestingStructured LoggingGitBM25 + Dense Hybrid
Cyan-outlined tags = production-verified at depthAll skills backed by deployed code
Experience

Work History

Production systems across public sector and enterprise — not prototypes.

Aug 2025 — Present
Deloitte South Asia LLP
Assistant Manager — Data Scientist (GenAI)
Mumbai, India
  • Architected production-grade LLM backend services in Python with Pydantic schema validation, structured outputs, retry logic, and circuit-breaker error handling — improving downstream reliability across multi-agent consumers.
  • Designed and optimized LLM-powered analytics and AI-assisted code-generation workflows enabling business users to convert natural-language requests into validated SQL queries and structured business insights with rule-based guardrails.
  • Built tool-calling and function-calling pipelines for autonomous agent workflows using LangGraph, supporting decision-support automation and downstream multi-agent task orchestration.
  • Deployed scalable GenAI services on Azure Functions and App Service with Docker containerisation and automated CI/CD pipelines via Azure DevOps.
  • Implemented full LLMOps observability stack — MLflow experiment tracking, LangSmith tracing, Pytest regression suites, and Locust load testing — validating production reliability under concurrent user load.
LangGraphMCPLLMOpsRAGASAzureDatabricksDockerCI/CD
Dec 2021 — Jun 2025
Government of Maharashtra
PC GenAI Analyst
Mumbai, India
  • Developed end-to-end NLP and Generative AI pipelines covering text preprocessing, chunking strategies, prompt engineering, and retrieval evaluation for citizen-facing public-sector applications.
  • Built embedding-based knowledge retrieval systems using FAISS, Chroma, and hybrid retrieval strategies — grounding LLM responses in authoritative government documentation and reducing hallucination risk in high-stakes contexts.
  • Designed automated document ingestion and indexing pipelines enabling continuous knowledge base updates at scale without service disruption.
  • Applied RAGAS evaluation frameworks to measure answer faithfulness, context relevance, and groundedness — driving iterative improvements with traceable, auditable outputs.
RAGFAISSRAGASPrompt EngineeringNLPHybrid Search
4+ years · 2 enterprise deploymentsAvailable immediately for global remote roles
Projects

Featured Work

6 production systems and portfolio repos — backed by real code and real metrics.

PROJECT_01 · FLAGSHIP
Multi-Agent OKR Analytics System
Azure · LangGraph · Multi-Agent · Databricks · LLMOps
  • LangGraph multi-agent orchestration with intent-classification routing to specialist agents — analytics, reasoning, code execution, retrieval
  • Tool-calling for autonomous Databricks dataset querying and validated code execution
  • Audit-ready traceability via LangSmith for enterprise compliance
  • Human-in-the-loop review gates balancing autonomy with governance
LangGraphLLMOpsAzure
github / langgraph-task-orchestrator
PROJECT_02
Advanced RAG Chatbot for Knowledge Retrieval
RAG · Hybrid Search · FAISS · Chroma · RAGAS Evaluation
  • Dense embeddings + hybrid search (semantic + keyword) over FAISS and Chroma — evidence-grounded, low-hallucination responses
  • Iterative prompt tuning, re-ranking strategies, and RAGAS-driven evaluation cycles
  • Structured fallback handling and confidence thresholds routing ambiguous inputs to human review
RAGRAGASHybrid Search
github / advanced-rag-chatbot
PROJECT_03
MCP Tool Server
Model Context Protocol · LangGraph · Dynamic Tool Discovery
  • Custom MCP server exposing domain tools with dynamic tool discovery and manifest-based calling
  • Standardised tool protocol enabling agent-agnostic, reusable tool servers across multiple LangGraph agents
  • Runtime tool registration — a rare and in-demand capability in 2026 JDs
MCPLangGraph
github / mcp-tool-server
PROJECT_04
Hybrid RAG Engine
BM25 · Dense Embeddings · Cross-Encoder · Self-RAG · GraphRAG · Pinecone
  • BM25 + dense hybrid search with Reciprocal Rank Fusion — built from scratch, not abstracted
  • Two-stage retrieval: fast hybrid → accurate cross-encoder re-ranking
  • Self-RAG loop + GraphRAG via Microsoft open source for structured knowledge retrieval
GraphRAGSelf-RAGLlamaIndex
github / hybrid-rag-engine
PROJECT_05
RAG Eval Harness with CI/CD Gate
DeepEval · RAGAS · LLM-as-Judge · GitHub Actions · MLflow
  • Custom LLM-as-Judge evaluator — scores faithfulness 1–5 with structured reasoning
  • Full RAGAS suite automated with Pytest; GitHub Actions CI/CD gate blocks deployment if faithfulness < 0.75
  • MLflow experiment tracking — prompt A/B comparison with metric visualisation
DeepEvalLLM-as-JudgeCI/CD Gate
github / rag-eval-harness
PROJECT_06
Production Agent on AKS
FastAPI · Docker · Kubernetes AKS · PydanticAI · Locust · GitHub Actions
  • FastAPI backend wrapping LangGraph agent with PydanticAI output validation on all LLM responses
  • Docker containerised → Azure Kubernetes Service (AKS) via GitHub Actions CI/CD pipeline
  • CI pipeline runs full RAGAS eval on every commit — Locust load tested at 100 concurrent users
KubernetesFastAPIPydanticAI
github / production-agent-aks
All 6 repos open on GitHubClick any card to expand full details
Contact

Let's build something real.

Send a message directly — I read every one. Typical response within 24 hours.

Your message goes directly to ag.chaudhari.1512@gmail.com
Availability
Open to senior Agentic AI / LLM Engineer roles — production-grade systems, not prototypes.
Available for interviews immediately
EU / UK / US timezone overlap — async-remote
Mumbai on-site / hybrid also considered
Notice period: standard as per Deloitte policy
Akash Chaudhari · Agentic AI Engineer · 2026Mumbai, India
Interactive Lab

Play with AI concepts

Three mini-games built around the exact systems I build at work. See how well you know Agentic AI.

🎯
Hallucination Hunter
Spot the bad RAG output
🏗️
Agent Architect
Build the right pipeline
Stack Matcher
Match tools to definitions