AI Engineer VP

What you'll do

• Build autonomous systems that reason, use tools, and complete multi-step tasks using LLMs and reasoning models.
• Develop calibration scoring and guardrails to ensure the accuracy of AI agents.
• Design, implement, and operationalize distributed, scalable data flows for batch and real-time data processing.
• Build and deploy AI agents at scale to accelerate technology and business roadmaps.
• Evaluate state-of-the-art Gen AI technologies and prototype solutions to improve architecture and platforms.
• Demonstrate the "Art of the possible" through Proof of Concepts (POCs) to accelerate AI adoption.
• Manage the cloud adoption and engineering roadmap to ensure scalable and robust architecture.
• Integrate external APIs as agent tools, including function calling and error handling for model outputs.

What we're looking for

• 6+ years of experience building GenAI solutions and supporting components design, architecture, development, and operationalization of agent orchestrations at scale.
• Mastery of agent orchestration frameworks such as LangChain, LangGraph, CrewAI, and Microsoft's AutoGen.
• Deep expertise in LLM APIs (OpenAI, Anthropic, AWS Bedrock), prompt engineering, and fine-tuning for agentic behaviors.
• Ability to implement complex memory systems, including vector databases (Pinecone, Weaviate) and Retrieval-Augmented Generation (RAG) pipelines.
• Proficiency in integrating external APIs as agent tools, including function calling and error handling for malformed model outputs.
• Expert-level Python (mandatory) and familiarity with FastAPI, Node.js, or Go.
• Familiarity with Docker and Kubernetes for containerized deployment.
• Good written and verbal communication skills.