AI Engineer

What you'll do

• Build autonomous systems that use LLMs/Reasoning models to perform multi-step tasks and tool usage.
• Develop calibration scoring and guardrails to ensure accuracy for AI agents.
• Evaluate state-of-the-art Gen AI technologies and prototype solutions to improve architecture and platforms.
• Design, implement, and operationalize distributed, scalable data flows for batch and real-time processing.
• Build multi-agent workflows using frameworks like LangChain, LangGraph, CrewAI, or Microsoft AutoGen.
• Implement complex memory systems including vector databases and Retrieval-Augmented Generation (RAG) pipelines.
• Integrate external APIs as agent tools with robust function calling and error handling.
• Contribute to the overall cloud adoption and engineering roadmap for scalable and reliable infrastructure.

What we're looking for

• Candidates must have at least 2 years of experience building GenAI solutions and supporting agent orchestration architecture.
• Mastery of agent orchestration frameworks such as LangChain, LangGraph, CrewAI, and Microsoft's AutoGen is required.
• Deep expertise in LLM APIs (OpenAI, Anthropic, AWS Bedrock), prompt engineering, and fine-tuning is required.
• Ability to implement complex memory systems including vector databases and RAG pipelines is required.
• Proficiency in integrating external APIs as agent tools with function calling and error handling is required.
• Expert-level Python skills are mandatory, with familiarity in FastAPI, Node.js, or Go.
• Familiarity with Docker and Kubernetes for containerized deployment is standard.