Description

You will build, deploy, and optimize production-grade GenAI applications and agentic workflows. This role owns the end-to-end lifecycle from architecture design to monitoring and cost optimization.

This role is on-site.

Responsibilities

• Develop agentic AI workflows using CrewAI, AutoGen, LangGraph, or LangChain Agents.
• Design and implement RAG pipelines, vector search solutions, and embedding-based retrieval systems.
• Build scalable AI services using Python, FastAPI, or Flask on cloud platforms (Azure/AWS/GCP).
• Implement hallucination reduction, prompt engineering, and model evaluation strategies.
• Integrate LLMs with enterprise applications, APIs, and automation workflows while monitoring performance.

Required Skills

• 5–10+ years of experience in Python-based backend engineering and AI/ML system development.
• Strong hands-on expertise with Generative AI, LLMs (OpenAI, Azure OpenAI, Claude, Gemini, Llama), and RAG.
• Proficiency in agentic frameworks such as LangChain, LangGraph, CrewAI, or AutoGen.
• Experience building production-ready APIs and services using FastAPI or Flask.
• Knowledge of vector databases (FAISS, Pinecone, Chroma, Weaviate) and semantic search.
• Understanding of distributed systems, async processing, Kafka/queues, and backend scalability.
• Hands-on exposure to cloud platforms (Azure, AWS, GCP), CI/CD, and MLOps/LLMOps practices.

Preferred Skills

• Experience in regulated or enterprise domains (e.g., Banking/KYC/Onboarding).

Key Skills

Education

Any Graduate