Forward Deployed Engineer

A well-funded, early-stage AI company building an agent-first research platform for finance is hiring a Forward Deployed Engineer to bring clients' proprietary data into the product and turn it into something they use every day. The platform is already in daily use by dozens of financial institutions.

You'll work with clients to understand what data they hold and how it shapes their workflow, then build the pipeline that ingests it, makes it searchable by the research agent, and delivers it as a dashboard, workflow, agent or report. The data is a means to an end; what matters is the tool the client ends up using every day.

It's a hands-on engineering role for someone who wants to work end to end, from the first client conversation to a working deliverable.

Company Culture On-site in New York, working closely with the founding team Founded by a small team with strong finance and technical research backgrounds Product used in live, high-stakes work by both sell-side and buy-side firms Backed by a well-known syndicate of financial and venture investors Small team where each deployment is tailored to the client rather than built on a fixed template A team that works out what a good agentic system looks like together, with evaluation central to how they build What's on Offer Salary up to $220k, dependent on experience Client exposure from day one, building complete solutions rather than a single feature Seat close to the founders on a system already in production use at scale What You'll Be Doing Working directly with clients, often before they know what they want, to understand their internal data (SharePoint reports, portfolio and quantitative data, structured and unstructured) and how it feeds their daily workflow Ingesting that data into the platform's core pipeline: connectors, parsing and chunking, and LLM metadata extraction with source provenance for citation Designing the search and retrieval layer so the research agent decides what to read and can see how it got there, across both client and public data Delivering the result in the format that fits the client's day: dashboard, workflow, agent or report Making improvements measurable through extraction-quality evals and search precision/recall Building on top of the existing platform for each client rather than maintaining one fixed system What We're Looking For The Person: A hands-on engineer who has built something end to end and can explain in technical detail what they built, which parts were theirs, why, and what they would change now Has taken a system from small scale to production, ideally with client-specific requirements; startup and large-company backgrounds are both fine if the end-to-end ownership is real Comfortable in client conversations, and clear, direct and concise when explaining technical work Current on retrieval and agent-based approaches, and open to moving on from architectures you've used before Finance experience is not required The Tech: Strong Python experience across modern async web frameworks and ORMs Hands-on experience building search or retrieval systems that an LLM agent uses to find and read information Experience with at least one search or data store technology (e.g.

OpenSearch, Elasticsearch, PostgreSQL) Exposure to multi-model LLM extraction chains and structured outputs Some backend TypeScript experience is a plus Active use of coding agents (e.g. Claude Code, Cursor, Codex) as part of daily practice If this sounds like your kind of role, feel free to reach out for a confidential chat.