Senior AI Engineer

Role overview

As a Senior AI Engineer at Teak, you will lead and build an agentic layer that turns Teak’s existing platform APIs into AI-native, compliant refund solutions. This is a hands-on engineering role responsible for production AI systems end-to-end, including design, deployment, and ongoing operation.

Responsibilities

• Agentic system design: Design, build, and maintain production-grade agentic systems, including multi-agent orchestration, specialist agents, and Human-in-the-Loop workflows (context management, memory, tool-calling).
• MCP & tool integration: Build MCP servers and develop tool integrations connecting AI agents to Teak’s platform APIs and partner systems.
• LLM integration & output control: Orchestrate LLMs (e.g., Claude, GPT, Gemini) across the AI layer, selecting appropriate models per task and enforcing prompt/system-prompt strategies for compliant, pre-approved language.
• RAG & knowledge systems: Build RAG pipelines grounded in Teak policy and product data, with versioning/isolation to reduce hallucinations on compliance-sensitive topics.
• Compliance & safety: Implement guardrails to enforce compliant offer language and prevent unauthorized coverage claims; meet regulatory requirements across Teak markets.
• Evaluation: Create evaluation frameworks to monitor, test, and continuously improve agent performance, reliability, and output quality.
• AI infrastructure & observability: Build and operate AI infrastructure on AWS, including structured logging and tracing for auditability and incident resolution.
• Backend development: Contribute to backend services/APIs in Python with clean code, testing, and strong engineering fundamentals.
• Collaboration & quality: Participate in code reviews, document integration patterns and system designs, work in Agile processes, and join an on-call rotation.

Requirements

• BS in Computer Science/Engineering or equivalent practical experience.
• 5+ years professional software engineering, including 2+ years focused on production AI/LLM application development.
• Strong Python and solid software engineering fundamentals.
• Deep backend experience designing, building, and operating production services and APIs (e.g., Django or similar), with testing, code quality, and system design strength.
• Hands-on experience with agentic AI systems (e.g., LangGraph, LangChain, AWS Bedrock Agents or similar).
• Experience integrating LLM APIs (e.g., Anthropic/OpenAI or similar) into production applications.
• Experience building and maintaining RAG pipelines and vector search systems.
• Working knowledge of Model Context Protocol (MCP) and tool-calling patterns.
• Experience designing and running LLM evaluation frameworks for quality, reliability, and safety.
• Experience operating AI infrastructure on AWS (or GCP/Azure).
• Strong written and verbal communication.

Nice-to-haves

• Not explicitly stated in the provided text.