Forward Deployed Engineer
- Discuss this with your agent
- Open in Claude
- Open in ChatGPT
Prepare application
- Draft this with your agent
- Open in Claude
- Open in ChatGPT
Role details
Tech stack
+5 more
Job description
This is the founding Forward Deployed Engineer role at Nimble. You build AI agents and search integrations with our customers and take them to production. After qualification, you partner with the Solution Consultant and customer engineers to refine the architecture and agree on success criteria. You build the first working version against the customerβs real queries, workflows, and codebase, and prove it on their evaluation set. You lead the implementation through production deployment and an agreed handoff, equipping the customerβs engineers to operate and extend what you build. A typical engagement lasts 12 weeks.
On each engagement, you own these technical decisions:
- Refining the implementation architecture.
- Choosing the appropriate orchestration approach.
- Defining evaluations with the customer.
- Negotiating technical scope and sequencing.
- Deciding what can be reused and what needs to remain customer-specific.
As the first member of the team, you help craft the strategy for the FDE function. That covers how we scope and run engagements, the playbook the team works from, and who we hire next.
The role is based in New York or San Francisco, 3 days a week in the office. This role reports to the Director of Solution Consulting. You do not carry a sales quota., * Turn the customerβs goal into a working flow of Search, Extract, and Web Search Agent calls, wired into the customerβs own code.
- Build the first version on the customerβs real queries, side by side with the customerβs engineer.
- Define representative evaluation sets and success criteria with the customer. Benchmark quality, latency, and cost as you iterate, and instrument production workflows to detect failures and regressions.
- Write the orchestration code that keeps the flow stable in production, with fan-out, dedupe, retries, and cost caps.
- Embed Nimble in the customerβs agent through our MCP server, our SDKs, or the API, on a schedule or on demand.
- Present results to the customerβs engineers and executives, and record the technical win with the Solution Consultant.
- Write the runbook, train the customerβs engineer, and hand the account 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: the engagement model, the entry and exit criteria, the playbook, and the profile of the next hires.
Requirements
- You write production Python and can read and change TypeScript.
- You have shipped and operated LLM-powered applications for real users, and can explain how you handled failures and managed latency and cost at each step.
- You have designed or improved evaluations for an LLM or other nondeterministic system, and used the results to make engineering decisions.
- You have built tools for an agent to call, through MCP, function calling or an equivalent., * You have 4+ years of software engineering and can show LLM or agent work you shipped, such as a repo, a live product or a case study.
- You have worked directly with customers or external partners to scope and deliver technical projects, whether as an FDE, software engineer, solutions engineer, consultant, or founder.
- You can run a discovery call with a VP and debug a failing run with an engineer on the same day.
- You are comfortable with ambiguity and rapid change in a fast-paced startup., * You have worked on retrieval and RAG, including hybrid search, reranking, and freshness.
- You have built with LangGraph, the OpenAI Agents SDK, the Vercel AI SDK, or the Claude Agent SDK.
- You have delivered data to Snowflake or Databricks.
- You have worked with web data, such as scraping, anti-bot systems, and structured extraction.
- You use AI development tools effectively and take responsibility for reviewing, testing, and maintaining the code they produce
Benefits & conditions
Base pay is $170K to $235K, depending on level. The package adds 10% to 15% variable pay and equity.
Apply for this position
This job is hosted externally. Click below to view the full posting and apply.
Prepare application
- Draft this with your agent
- Open in Claude
- Open in ChatGPT
Good distractions
Loading talks and stories from around this roleβ¦