Description

You will design, develop, and implement complex Gen AI solutions for high-visibility summarization and chatbot projects handling large volumes of multi-type documents.

This role is hybrid.

Responsibilities

• Lead the end-to-end development of Gen AI applications using LLMs (Llama, Mixtral, Mistral) and frameworks like Langchain and LlamaIndex.
• Build and optimize inference pipelines using transformer/pipeline, vLLM, and agentic frameworks like LangGraph.
• Implement evaluation frameworks (RAGAS, LangSmith, Phoenix-Arize) and embedding models to ensure system accuracy.
• Develop REST APIs and WebSockets using FastAPI, integrating with enterprise databases like Redis, Qdrant, and Cockroach.
• Ensure model governance compliance by writing model documentation and building monitoring capabilities.

Required Skills

• 5+ years of professional experience in data science or AI engineering.
• Strong proficiency in Python for executing end-to-end Gen AI projects.
• Hands-on experience with LLM models (Llama, Mixtral, Mistral) and inference mechanisms.
• Expertise in Langchain, LlamaIndex, and LangGraph for agentic workflows.
• Experience with evaluation tools such as RAGAS, LangSmith, or Phoenix-Arize.
• Knowledge of embedding models (e.g., all-MiniLM-L6-v2, all-mpnet-base-v2).
• Proficiency with REST API, FastAPI, and Websockets.
• Experience with Model Risk Management and governance guidelines.

Preferred Skills

• Experience with Angular for frontend integration.
• Familiarity with Slurm, Hadoop/Hive, Neo4J, Apache Spark, Kafka, or MongoDB.

Referral Bonus: ₹50,000

Key Skills

Education

Any Graduate