Staff AI Engineer

Staff AI EngineerWe're looking for a Staff AI Engineer to build intelligent systems that help professionals analyze complex private market data and make better investment decisions.This is a highly technical, product-focused role where you'll design and ship production AI systems from the ground up. You'll work across LLMs, retrieval, orchestration, backend infrastructure, and evaluation, helping define how AI becomes a core part of the product rather than an add-on.What You'll DoDesign and build production-grade AI systems powered by large language models.Develop agentic workflows that combine LLM reasoning with retrieval, structured data, APIs, and external tools.Build scalable RAG pipelines over large volumes of proprietary and unstructured financial data, including investment decks, filings, internal documents, and research materials.Improve AI performance through evaluation frameworks focused on reasoning quality, factual accuracy, latency, and cost.Develop observability and debugging systems for complex multi-step AI workflows.Partner closely with product and design to turn ambiguous problems into intuitive AI-powered user experiences.Mentor engineers and help establish best practices for building reliable, production-ready AI systems.What We're Looking For6+ years of software engineering experience with significant hands-on experience building AI-powered products.Strong Python and backend engineering fundamentals.Experience building applications with LLMs, including areas such as RAG, prompt engineering, agentic workflows, evaluation, or fine-tuning.Proven ability to take complex technical problems from idea through production.Strong systems design skills and sound engineering judgment.Product-minded engineer who enjoys solving real customer problems, not just building models.Comfortable operating in fast-moving, ambiguous environments with a high degree of ownership.Nice to HaveExperience building fintech, enterprise AI, or other data-intensive products.Background working with highly regulated or proprietary datasets.