Lead AI Engineer - Conversational AI & Semantic Search (Databricks / LangChain)

We are seeking aLead AI Engineer to design, build, and deploy an AI-powered chatbot/agent on Databricks, similar in architecture to an existing internal tool (LangGraph/LangChain orchestration + vector database semantic search) but applied to a new business use case. The ideal candidate can work independently, reverse-engineer/inherit concepts from prior implementations, and own the solution from prototype through production deployment.

Responsibilities

• Design and build a conversational AI / agentic application using LangChain and/or LangGraph, deployed on Databricks
• Implement semantic search / retrieval-augmented generation (RAG) pipelines using vector embeddings and a vector database (e.g., Databricks Vector Search, Chroma, Pinecone, FAISS)
• Define and tune similarity-matching logic (embedding models, distance metrics, thresholding, ranking of "% match" style results)
• Integrate with data sources (Databricks Unity Catalog tables, Delta Lake, APIs) to source and prepare the underlying knowledge base/corpus
• Own the ML/LLMOps lifecycle: experimentation, evaluation, versioning, deployment, and monitoring of the chatbot in production
• Collaborate with business stakeholders to translate a new use case into technical requirements
• Write clean, maintainable, well-documented Python code and establish testing and CI/CD practices for the AI application
• Ensure appropriate handling of data privacy, access control, and cost management (token usage, compute)

Requirements

• 5+ years of software/ML engineering experience, with at least 1 year working directly with LLM-based applications
• Proficiency in Python, including building, debugging, and refactoring production-grade code
• Expertise in LLM orchestration frameworks such as LangChain and/or LangGraph, including agent design, chains, tool calling, and state/memory management
• Skills in vector databases, embeddings, and semantic search, including generating embeddings, indexing them in a vector store, and implementing similarity search or RAG retrieval
• Familiarity with the Databricks platform, including notebooks, jobs, clusters, and Unity Catalog
• Experience calling and prompt-engineering against LLM providers such as OpenAI, Anthropic, and Azure OpenAI
• Bachelor's degree in Computer Science, Data Science, Engineering, or related field (or equivalent practical experience)
• Strong communication skills, with the ability to work with limited handoff documentation and ambiguous requirements
• English proficiency at B2 level or higher

Nice to have

• Knowledge of MLOps/LLMOps tooling such as MLflow, model/prompt versioning, and evaluation frameworks for LLM outputs
• Background in API/backend development using FastAPI, Flask, or similar, for exposing the chatbot as a service
• Familiarity with front-end/chat interface integration, wiring a backend agent to a chat UI