Full Stack Ai Engineer
About the Role
We are seeking a high-impact Full Stack AI Engineer to join the data intelligence function of a sophisticated financial services firm operating in the asset and investment management ecosystem. This role focuses on building production‑grade LLM‑powered applications that directly support internal decision‑making and business workflows. This is a full‑time position with a hybrid schedule based in the Chicago area. Candidates must be authorized to work in the United States. No visa sponsorship is available at this time. Job Title Full Stack AI Engineer (LLM Applications) Location Hybrid - Chicago, IL Responsibilities Build and ship production-ready LLM applications, including retrieval‑augmented generation (RAG) systems, internal AI assistants, and agent‑based workflows with strong UX Own features end‑to‑end across frontend, backend, and AI orchestration layers, including React/TypeScript interfaces, backend APIs, and LLM pipelines Design and implement RAG pipelines, including document ingestion, embeddings, vector search, reranking, grounding, and evaluation strategies Develop and integrate multi‑agent workflows using modern agentic frameworks and tooling Partner closely with cross‑functional teams (investment, research, product, operations, and business stakeholders) to translate real‑world requirements into scalable AI‑driven solutions Contribute to prompt design, evaluation methodologies, and cost/latency trade‑off decisions for LLM deployments Collaborate with engineering peers on system design, architecture, security, and observability in a regulated environment Required Skills & Experience 3‑6+ years of experience in software engineering, full stack engineering, AI engineering, or related roles, with demonstrated production delivery Hands‑on experience building and shipping LLM‑powered applications in production environments Strong proficiency in TypeScript/React and/or Python with modern backend frameworks (e.g., FastAPI) Experience designing and implementing RAG systems end‑to‑end, including vector database integration Familiarity with agentic workflows, multi‑agent systems, and related orchestration frameworks Experience working with AWS‑based AI platforms and cloud infrastructure (LLM deployments, observability, CI/CD) Strong SQL skills and experience with relational databases such as Postgres or cloud‑native equivalents Experience integrating secure authentication and authorization patterns (OAuth2, OIDC, SSO, RBAC) Financial services or regulated environment experience is a plus, but not required Compensation Base Salary Range: $150,000 - $165,000 Additional Information This is a hybrid role based in the Chicago area (on‑site and remote flexibility) Must be authorized to work in the United States — no visa sponsorship available Team operates in a high‑ownership, low‑bureaucracy environment focused on delivering real business impact Emphasis is on applied AI systems and production software, not standalone model research For more information or to apply, contact Ryan Dwyer at #J-18808-Ljbffr
Required Skills
Interested in this role?
Apply now and take the next step in your career.
