Key Responsibilities

• Design and develop Generative AI solutions using Python and leading LLM APIs (Claude, OpenAI, Azure OpenAI)
• Build and optimize RAG (Retrieval-Augmented Generation) pipelines and integrate vector databases
• Design and implement MCP (Model Context Protocol) servers for AI applications
• Develop AI agent frameworks using LangChain, AutoGen, or CrewAI
• Collaborate with cross-functional teams to integrate AI capabilities into enterprise solutions
• Evaluate, benchmark, and fine-tune large language models for specific use cases
• Maintain and improve existing AI/ML pipelines and infrastructure
• Document architectures, APIs, and implementation patterns for AI solutions

Requirements

• Strong proficiency in Python for AI/LLM development
• Hands-on experience building RAG pipelines and working with vector databases (e.g., Pinecone, Weaviate, Chroma, FAISS)
• Experience with LLM API integration including Claude (Anthropic), OpenAI, and/or Azure OpenAI
• Practical knowledge of MCP (Model Context Protocol) server design and implementation
• Experience with AI agent frameworks such as LangChain, AutoGen, or CrewAI
• Strong understanding of prompt engineering and LLM evaluation techniques
• Bachelor's degree in Computer Science, Engineering, or a related field
• Excellent problem-solving and communication skills

Skills Required