AI Engineer

AI Engineer role in New York, NY (hybrid) at Farsight AI focused on building agentic AI systems and pipelines that generate client-ready financial deliverables while advancing evaluation, retrieval, and platform capabilities.

Responsibilities

• Design, implement, and own end-to-end agentic systems that produce decks, models, and memos for clients, from data ingestion to polished output.
• Develop evaluation and quality controls for generated deliverables, including deterministic checks, model-based reviews, grounding and fidelity verification, and regression suites for non-deterministic outputs.
• Turn proprietary platform and client data into evidence-backed insights by building pipelines that discover, quantify, and verify patterns, feeding them back into how drafts and checks are performed.
• Architect and refine retrieval mechanisms that ground deliverables in unstructured and structured financial data, ensuring every figure traces back to a source.
• Advance the next generation of agentic capabilities on the Farsight platform, including composability, advanced function calling, and modular orchestration.
• Shape the product roadmap by prioritizing customer value, time-to-market, execution risk, and projected impact.

Requirements

• 2+ years deploying machine learning or large language model systems in production environments.
• Experience building agentic systems with function calling, tool integration, orchestration, and reliability engineering to keep multi-step processes on track.
• Proven ability to build and validate evaluations for LLM systems; avoid relying on simplistic one-number ratings.
• Experience implementing retrieval over both unstructured and structured data, including handling documents as structured artifacts with mixed text, numeric, and tabular content, plus analysis of rendered output.
• A practical, AI-assisted development workflow with a verification story proportional to the tasks delegated.
• Strong Python proficiency and current fluency with frontier model APIs and their capabilities.

Technologies

• Python
• Frontier model APIs

Compensation & Benefits

• Salary: USD 200,000 to 300,000 per year, commensurate with experience.
• Comprehensive medical, dental, and vision insurance.
• Unlimited paid time off.

Above and Beyond Qualifications

• Experience evaluating generated documents or other complex, client-facing deliverables, combining deterministic checks with model-based judgment.
• Experience extracting reliable, quantified patterns from large, noisy real-world datasets, with evidence-backed findings.
• Deep familiarity with financial data, documents, and workflows.