Forward Deployed Engineer

NimbleWay•New York, NY

3d•Hybrid

About The Position

This is Nimble’s founding Forward Deployed Engineer role. The engineer builds AI agents and search integrations with customers and takes them to production. After qualification, they work with the Solution Consultant and customer engineers to refine the architecture, agree on success criteria, build an initial version using the customer’s real queries, workflows, and codebase, and validate it against the customer’s evaluation set. They lead implementation through production deployment and handoff, preparing customer engineers to operate and extend the solution. A typical engagement lasts 12 weeks. The role owns technical decisions for each engagement, including implementation architecture, orchestration approach, evaluations, technical scope and sequencing, and what should be reusable versus customer-specific. As the first member of the FDE team, the engineer also shapes the function’s strategy, engagement model, playbook, hiring profile, and future hires. The role is based in New York or San Francisco, with three days a week in the office, and reports to the Director of Solution Consulting. It does not carry a sales quota. Nimble builds AI web search products that give businesses programmatic access to the web for AI agents. Its products serve businesses in financial services, retail, market intelligence, and coding. Nimble has raised over $70 million and has hundreds of enterprise customers.

Requirements

At least 4 years of software engineering experience.
Production Python skills and the ability to read and modify TypeScript.
Experience shipping and operating LLM-powered applications for real users, including explaining how failures, latency, and cost were managed.
Experience designing or improving evaluations for an LLM or another nondeterministic system and using the results to make engineering decisions.
Experience building tools for agents to call through MCP, function calling, or an equivalent approach.
Demonstrable shipped LLM or agent work, such as a repository, live product, or case study.
Experience working directly with customers or external partners to scope and deliver technical projects.
Ability to lead discovery conversations with senior executives and debug technical issues with engineers.
Comfort with ambiguity and rapid change in a fast-paced startup.

Nice To Haves

Experience with retrieval and RAG, including hybrid search, reranking, and freshness.
Experience with LangGraph, the OpenAI Agents SDK, the Vercel AI SDK, or the Claude Agent SDK.
Experience delivering data to Snowflake or Databricks.
Experience with web data, including scraping, anti-bot systems, and structured extraction.
Effective use of AI development tools, with responsibility for reviewing, testing, and maintaining the code they produce.

Responsibilities

Turn customer goals into working flows of Search, Extract, and Web Search Agent calls integrated with the customer’s code.
Build an initial version using the customer’s real queries, working alongside the customer’s engineer.
Define representative evaluation sets and success criteria with customers.
Benchmark quality, latency, and cost during iteration, and instrument production workflows to detect failures and regressions.
Write orchestration code to support stable production workflows, including fan-out, deduplication, retries, and cost caps.
Integrate Nimble into customer agents through its MCP server, SDKs, or API, on a schedule or on demand.
Lead implementations through production deployment and an agreed handoff.
Present results to customer engineers and executives, and record technical wins with the Solution Consultant.
Write runbooks, train customer engineers, and hand accounts to Customer Success.
Identify recurring customer needs and turn successful implementations into reusable integrations, evaluation tools, reference applications, and product improvements.
Shape the FDE function, including its engagement model, entry and exit criteria, playbook, and future hiring profile.