Lead design and implementation of production agentic AI systems that integrate LLMs with Teak's platform APIs. Build RAG pipelines, MCP/tool integrations, evaluation frameworks, and AI infrastructure on cloud (AWS/GCP/Azure). Contribute backend services in Python, ensure compliance and safety, and operate systems in production including observability and on-call duties.
About Teak
Teak is reinventing refunds, striving to make every experience refundable. Our proprietary SaaS embedded refund protection platform provides massive distribution and a top-tier digital purchasing experience for insurance carriers, event organizers, booking platforms, ticketing systems, and their consumers — embedded in millions of carts each month.
Role Overview
As AI-powered commerce becomes a new standard, Teak is building an agentic layer on top of our established platform APIs, letting partner AI agents offer, explain, and fulfill refund solutions compliantly and without friction at the point of purchase. As a Senior AI Engineer, you'll help lead and build that layer end-to-end: architecting the agentic systems, integrations, and infrastructure that turn our existing APIs into AI-native capabilities. This is a hands-on engineering role for someone who owns production AI systems from design through deployment and operation, well beyond prompt work, while staying closely connected through code reviews, technical discussions, and regular team syncs.
This is an excellent opportunity to make a meaningful impact at a rapidly growing company at the forefront of agentic commerce.
Key Responsibilities- Agentic System Design: Design, build, and maintain production-grade agentic systems, multi-agent orchestration, specialist agents, and Human-in-the-Loop workflows, with context management, memory, and tool-calling.
- MCP & Tool Integration: Develop MCP servers and tool integrations connecting AI agents to Teak's platform APIs and partner systems.
- LLM Integration & Output Control: Orchestrate LLMs (Claude, GPT, Gemini, or similar) across the AI layer, selecting the right model per task and managing prompt and system-prompt strategies so agents present refund solutions in pre-approved, compliant language.
- RAG & Knowledge Systems: Build RAG pipelines that ground agent responses in Teak's policy and product data, with versioning and isolation that prevent hallucination on compliance-sensitive topics.
- Compliance & Safety: Implement guardrails that enforce compliant offer language, prevent unauthorized coverage claims, and meet regulatory requirements across Teak's markets.
- Evaluation: Build evaluation frameworks to monitor, test, and continuously improve agent performance, reliability, and output quality.
- AI Infrastructure & Observability: Build and operate AI infrastructure on AWS, with structured logging and tracing for auditability and rapid issue resolution.
- Backend Development: Contribute to backend services, APIs, and platform improvements in Python alongside AI work, applying clean code, testing, and strong engineering fundamentals.
- Collaboration & Code Quality: Participate in code reviews, document agent system design and integration patterns, take part in Agile workflows, and join the on-call rotation.
Required:
- Bachelor's Degree in Computer Science, Engineering, a related field, or equivalent practical experience.
- 5+ years of professional software engineering experience, with at least 2 years focused on production AI/LLM application development.
- Strong Python proficiency and solid software engineering fundamentals.
- Deep backend engineering experience, designing, building, and operating production services and APIs (Django or similar framework), with strong fundamentals in testing, code quality, and system design.
- Hands-on experience building and deploying agentic AI systems (LangGraph, LangChain, AWS Bedrock Agents, or similar).
- Demonstrated experience integrating LLM APIs (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 building and operating AI infrastructure on a major cloud platform (AWS, GCP, or Azure).
- Strong written and verbal communication, with the ability to explain AI system design to technical and non-technical stakeholders.
- Fully remote position; reliable internet connection and an appropriate home office workspace required.
- Background in a compliance-sensitive industry (insurance, fintech, legal) where regulated AI output and guardrails matter.
- Experience operating LLM systems at high volume, with attention to latency, cost, and caching.
- Familiarity with AWS Bedrock or similar managed AI platforms and agent runtimes.
- Experience with model fine-tuning, customization, or distillation.
- Contributions to open-source AI tooling or frameworks.
- Fully Remote Working Environment
- Competitive Salary and Equity Opportunities
- Unlimited Paid Time-off
- Medical, Dental, and Vision Benefits
- Annual Bonus Program
- 401k Matching
- $100/month for Event Ticket Purchase
- Company Sponsored Events
Similar Jobs
Fintech • Software • Financial Services
Build the core AI platform and high-performance Rust backend powering an AI-native trading copilot. Implement streaming responses, low-latency tool execution, caching, orchestration of models and tools, secure APIs, auditing/tracing, and safe, auditable trading action infrastructure. Partner with product and frontend to enable AI-native UX and translate trading domain requirements into resilient platform primitives.
Top Skills:
CachingLlm ApisModel ServingPostgresReactReact NativeRustStreamingTokio/AsyncTypescript
Fintech • Software • Financial Services
Lead ownership of reliability, evaluation, and safety for an AI copilot in a trading platform. Build eval systems, benchmarks, automated quality gates, monitoring, and model improvement loops; partner with engineering and product to define safe tool contracts and ensure predictable, auditable assistant behavior in trading workflows.
Top Skills:
Eval PipelinesLlm ApisModel ServingObservability/Telemetry ToolingPostgresReactReact NativeRustTraining PipelinesTypescript
Artificial Intelligence • Consumer Web • Digital Media • Information Technology • Social Impact • Software
Build end-to-end full-stack AI features on a Ruby on Rails backend and React frontend, design and run experiments (A/B tests and AI evaluations), implement AI infrastructure for reliable LLM inference, and iterate quickly to scale production-ready LLM-powered products.
Top Skills:
Ai AgentsLlmsMySQLPostgresReactRetrieval-Augmented Generation (Rag)Ruby On Rails
What you need to know about the Chicago Tech Scene
With vibrant neighborhoods, great food and more affordable housing than either coast, Chicago might be the most liveable major tech hub. It is the birthplace of modern commodities and futures trading, a national hub for logistics and commerce, and home to the American Medical Association and the American Bar Association. This diverse blend of industry influences has helped Chicago emerge as a major player in verticals like fintech, biotechnology, legal tech, e-commerce and logistics technology. It’s also a major hiring center for tech companies on both coasts.
Key Facts About Chicago Tech
- Number of Tech Workers: 245,800; 5.2% of overall workforce (2024 CompTIA survey)
- Major Tech Employers: McDonald’s, John Deere, Boeing, Morningstar
- Key Industries: Artificial intelligence, biotechnology, fintech, software, logistics technology
- Funding Landscape: $2.5 billion in venture capital funding in 2024 (Pitchbook)
- Notable Investors: Pritzker Group Venture Capital, Arch Venture Partners, MATH Venture Partners, Jump Capital, Hyde Park Venture Partners
- Research Centers and Universities: Northwestern University, University of Chicago, University of Illinois Urbana-Champaign, Illinois Institute of Technology, Argonne National Laboratory, Fermi National Accelerator Laboratory
