Description

You will design, develop, and deploy customized LLM-based applications and scalable Generative AI solutions on the Databricks Lakehouse architecture.

This role is hybrid.

Responsibilities

• Build RAG solutions, fine-tune LLMs, and develop prompt engineering frameworks.
• Implement AI orchestration workflows using Databricks Mosaic AI, MLflow, and Unity Catalog.
• Develop vector databases, embeddings pipelines, and semantic search integrations.
• Optimize model performance, inference latency, and cost efficiency in production.
• Ensure AI governance, monitoring, and security while collaborating with product teams.

Required Skills

• 5+ years of experience with Python and SQL.
• Strong hands-on expertise with Databricks, Mosaic AI, and Delta Lake.
• Experience with LLMs (GPT, Llama, Mistral, Claude) and RAG architectures.
• Proficiency in AI orchestration frameworks like LangChain or LangGraph.
• Knowledge of cloud platforms (AWS, Azure, or GCP) and containerization (Docker, Kubernetes).
• Familiarity with vector databases (Pinecone, FAISS, ChromaDB) and semantic search.
• Understanding of MLOps, CI/CD, and model evaluation practices.

Preferred Skills

• Experience deploying GenAI applications in enterprise environments.
• Knowledge of distributed computing and Spark optimization.

Key Skills

Education

Any Gradute