Job Responsibilities:
Develop AI applications using Python and LLMs for enterprise use cases
Design agentic workflows involving planning, tool execution, memory, and feedback loops
Implement prompt templates, tool/function calling, and structured outputs (JSON schemas)
Build Retrieval-Augmented Generation (RAG) pipelines using vector databases
Integrate AI solutions with APIs, message queues, and backend services
Implement guardrails, input/output validation, and error handling for LLM responses
Monitor latency, token usage, and response quality to optimize performance and cost
Contribute to solution architecture and technical design documentation'
Job Requirements:
Strong Python development experience with production systems
Hands-on experience with LLM APIs and open-source LLMs
Practical understanding of RAG, embeddings, chunking strategies, and similarity search
Experience with frameworks such as LangChain, LangGraph, AutoGen, CrewAI, Agno, or similar
Familiarity with vector stores (FAISS, Chroma, Pinecone, Weaviate, etc.)
Basic experience with cloud infrastructure and secure API integrations
Ability to reason about AI system behavior, limitations, and failure modes