Full Stack AI Engineer

Harbor Capital Advisors, Inc. • Chicago, IL

1d • $150,000 - $165,000 • Hybrid

About The Position

We are hiring a Full Stack AI Engineer to build production LLM applications: RAG-powered assistants, agent workflows, and internal AI applications with excellent UX. You will work on end-to-end features across React/TypeScript UI, backend APIs, and LLM orchestration on Amazon Bedrock, including Agents, prompt engineering, evaluation, and vector database integration techniques. You will partner closely with teams across Multi-Asset Solutions, Investment Research, Investment Products, Accounting, Marketing, and Distribution to turn real investment and business needs into production-grade tools that improve decision-making, efficiency, and client outcomes. Why Our Team? You’ll build production AI applications that directly support investment decision-making and client outcomes. We operate like a small, high-ownership team: fast iteration, real accountability, and a clear line of sight from what you ship to how the business invests and serves clients. You’ll collaborate closely with portfolio managers, quantitative analysts, and engineers, with the freedom to experiment and influence technical direction without getting trapped by legacy systems or slow, layered hierarchies. Who Will Thrive In This Role? This role is ideal for engineers who enjoy building AI powered software systems rather than developing standalone models. If your passion is designing and shipping LLM based applications such as retrieval augmented systems, agent workflows, and production grade AI services, you will thrive here. You should be comfortable owning features end to end, including contributing to front end components when needed to improve usability, workflow design, and overall user experience. We value engineers who think in terms of complete solutions, not just backend services. Our emphasis is on building reliable, scalable applications that apply LLMs to real business workflows.

Requirements

• Strong software engineering fundamentals with production experience in TypeScript/React and/or Python/FastAPI, (bonus: AI/chat/workflow UX, streaming responses).
• Hands-on experience shipping LLM applications into production.
• Experience designing RAG pipelines end-to-end: ingestion (parsing, chunking, embedding), retrieval (vector DB + filters), reranking, grounding/citations, and continuous evaluation.
• Experience using LLM coding tool like Claude Code, OpenAI Codex or GitHub Copilot.
• Experience designing and developing MCP and applications using agentic workflows.
• Strong SQL and experience with Postgres/Aurora or similar.
• Experience with Amazon Bedrock (models, guardrails, deployments, cost/latency tradeoffs).
• Experience building multi-agent systems using agentic frameworks (tools, workflows, evaluations, observability)
• Experience implementing vector database retrieval patterns (pgvector/OpenSearch/Pinecone/etc.)
• Experience integrating OAuth2/OIDC for secure authentication/authorization (SSO, token flows, RBAC).
• AWS experience (infrastructure, observability, CI/CD).
• Bachelor’s or Master’s degree in Computer Science, Engineering, Information Systems, or a related technical field. Degrees in Mathematics, Statistics, Economics, or similar quantitative disciplines are also welcome.
• 3 to 6 years of experience in Software Engineering, AI Engineering, Full Stack Engineering, Data Engineering, or related fields.
• Demonstrated experience shipping production LLM applications (regardless of years).

Nice To Haves

• Kubernetes/EKS and IaC (CloudFormation/Pulumi).
• Experience in regulated environments: auditability, PII handling, data entitlements.
• Exposure to data governance and security practices in cloud environments.
• Financial services industry experience is a plus but not required.
• Relevant professional or technical certifications are a plus.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level