Job Description:

Key Responsibilities :

- Design and develop AI agents and multi-agent systems for enterprise use cases.

- Build agentic workflows using frameworks such as LangChain, LangGraph, AutoGen, CrewAI or similar technologies.

- Develop LLM-powered applications using OpenAI, Azure OpenAI, Gemini, Claude or equivalent models.

- Implement RAG pipelines using vector databases and enterprise knowledge sources.

- Integrate AI agents with APIs, databases, enterprise applications, search engines, and external tools.

- Develop agent capabilities including planning, reasoning, memory, tool calling, task decomposition, and decision-making.

- Build prompt engineering strategies and optimize LLM responses for accuracy and reliability.

- Work with Python to develop scalable AI services and backend applications.

- Implement evaluation, monitoring, guardrails, observability, and responsible AI practices.

- Fine-tune or customize models where required and optimize inference performance.

- Deploy AI solutions on AWS, Azure, or GCP using containers and CI/CD pipelines.

- Collaborate with Data Scientists, ML Engineers, Software Engineers, Architects, and business teams.

- Troubleshoot and improve the performance, scalability, security, and reliability of AI applications.

Required Skills :

- Strong programming experience in Python.

- Hands-on experience with Generative AI and Large Language Models (LLMs).

- Strong understanding of Agentic AI concepts and autonomous AI workflows.

- Experience with LangChain / LangGraph / AutoGen / CrewAI or similar frameworks.

- Strong knowledge of RAG, embeddings, vector databases, semantic search, and knowledge retrieval.

- Experience with prompt engineering and LLM orchestration.

- Experience integrating REST APIs, tools, function calling, and enterprise systems.

- Knowledge of FastAPI, Flask, or similar Python frameworks.

- Experience with databases such as PostgreSQL, MongoDB, SQL Server or similar.

- Experience with vector databases such as Pinecone, FAISS, Chroma, Weaviate, Milvus or equivalent.

- Understanding of ML/AI lifecycle, model evaluation, monitoring, and deployment.

- Good understanding of cloud platforms such as AWS, Azure, or GCP.