Suvom Karak
ML Engineer
5+ years exp
5+ years ML exp
Python
JavaScript
Node JS
TypeScript
SQL
Active 2 days ago
+91 (8777) 061431
Invite to interview
Message
Download CVCV
Overview
Technical skills
Timeline
Roles
Overview
ML engineer focused on production delivery of LLM and ML systems, including agentic orchestration and RAG-based document and knowledge search. Experienced in building backend services with Python APIs (Flask/FastAPI), integrating with internal systems, and operating production quality pipelines with observability, evaluation, and guardrails.
Technical skills
Python
JavaScript
Node JS
TypeScript
SQL• Junior
Python
FastAPI• 5y+
Flask• 5y+
Pydantic
Databases
pgvector
Qdrant
ElasticSearch
DynamoDB
OpenSearch
PostgreSQL
AI/ML
Arize Phoenix
AWS Bedrock
Claude
Claude Code
Cursor
Fine-tuning
Gemini
Google ADK
Hybrid Search
LangSmith
PyTorch
Semantic Search
Transformers
Vertex AI
LLM• 5y+
RAG• 5y+
LangChain• 4y+
Guardrails AI
Langfuse
LangGraph
DevOps
Azure
CI/CD
Docker
Rest API
Vector
Vercel
WebSockets
AWS
AWS Lambda
OpenTelemetry
Timeline
Senior ML / AI Engineer
•
Senior
Deloitte US
•
Full-Time
Built and productionized an internal-assistant platform using an agentic FastAPI gateway, including session identity, graph lifecycle, state persistence, and streaming. Designed LLM orchestration with LangGraph using structured outputs, follow-up-aware routing, tool-based handoff, and SQL query validation with self-correction. Implemented human-in-the-loop control with LangGraph interrupt/resume and durable execution via Postgres checkpointing. Added request guardrails, MCP tool discovery, and production observability with Langfuse and OpenTelemetry tracing plus model-quality evaluation.
LangGraph
Pydantic
PostgreSQL
SQL
Guardrails AI
Langfuse
OpenTelemetry
AWS
AWS Lambda
DynamoDB
OpenSearch
ML / AI Engineer
•
Middle
Tata Consultancy Services
•
Full-Time
Developed production LLM applications on Azure OpenAI for enterprise document processing and semantic search across large knowledge bases. Engineered RAG and semantic-search pipelines using vector similarity indexing and built automated extraction, chunking, and categorization. Delivered backend services for document analysis and multilingual translation/summarization using Flask/FastAPI, integrating with internal systems under security constraints. Created an end-to-end agentic pipeline for recruitment operations with LangChain and supported model evaluation, deployment, and ongoing production monitoring of quality and latency.
FastAPI
Flask
LangChain
RAG
LLM
Techno India University
Bachelor's Degree •
Electrical Engineering