AI Engineer

What you will do

• Build robust backend services and APIs using Python (FastAPI, asyncio) for GenAI workflows and LLM-based systems.
• Develop and maintain GenAI applications using tools like LangChain, LangGraph, and Cohere, integrating them with custom APIs and data sources.
• Contribute to systems that enable intelligent routing of prompts, dynamic tool execution, and seamless model-data integration across multiple sources
• Write clean, modular code for model integration, semantic search, and multi-step agent workflows.
• Package and deploy applications using Docker and Kubernetes, ensuring scalability and security.
• Collaborate with data engineers, AI scientists, and infra teams to ship end-to-end features quickly, without sacrificing quality.

What you need to succeed

Must Have

• Strong backend development skills in Python
• Solid understanding of machine learning and generative AI
• Degree in Computer Science or Engineering
• Experience deploying services with Docker and Kubernetes in a cloud environment.
• Familiarity with LLM APIs (OpenAI, Cohere) and how to build prompt-based applications around them.
• Comfortable writing and debugging PySpark jobs and working with Delta Lake in Databricks.
• Experience working with Git workflows, CI/CD, and container-based deployments.

Nice to Have

• Experience with LangChain, LangGraph, or other LLM orchestration frameworks.
• Experience building and deploying MCP Servers, AI Agents
• Experience with any vector database.
• Experience with ML FLow