GenAI Engineer

Location: Hyderabad (Hybrid/Remote-friendly)About The RoleWe are building the infrastructure layer that connects AI agents to enterprise systems. We are looking for an experienced GenAI Engineer to join our founding engineering team. You will be responsible for building production-grade agentic workflows, orchestrating LLMs, and implementing RAG architectures that enterprise buyers can trust.What You Will OwnAgentic Frameworks: Architect and implement multi-step agent workflows using frameworks like CrewAI or LangChain. LLM Orchestration: Build secure, context-aware AI pipelines that integrate seamlessly with enterprise APIs and MCP protocols. Vector Infrastructure: Work closely with our Product Architect to evolve our RAG pipeline, embedding strategies, and vector database performance (Qdrant/Pinecone). Production Deployment: Develop and deploy reliable AI services that maintain high performance and cost-efficiency in production environments. What We Are Looking For3+ years of experience in machine learning or software engineering, with a primary focus on Generative AI. Hands-on experience with LLM integration, prompt engineering, and agentic framework development. Strong proficiency in Python (FastAPI) and experience building production-ready AI services. Understanding of vector databases (Qdrant, Pinecone) and the infrastructure patterns behind semantic retrieval. The "Ship, Not Slide" Mindset: You prioritize writing clean, deployable code over theory. You have a track record of shipping AI features that impact end-users Skills: pinecone,pytorch,prompt engineering,generative ai,fast api,python,llm,api,agentic ai,mcp,rag pipeline,quadrant,langchaon,langraph,embedding,crewai