Forward Deployed Engineer - Agents

Agents are only as good as the team behind them. We're experienced researchers and engineers building vertical AI agents that run in production inside some of the most demanding environments there are: health insurers, banks, and the public sector, where decisions are audited and mistakes carry real consequences.

We're looking for a forward-deployed engineer to embed with our customers in regulated industries, health insurers, banks, and the public sector, and turn their hardest operational bottlenecks into AI agents that actually run in production. This role is less about being a rockstar coder and more about being exceptional at understanding systems, using AI agents to move fast, and explaining the work clearly to everyone from client engineers to product and business stakeholders.

• Embed with customers. Work directly with operations teams and domain experts at health insurers, banks, and public institutions to understand their real workflows, then identify where an agent genuinely pays off, and where it doesn't.

• Scope and run workshops. Lead the buy-vs-build conversation per use case: is there a real backlog, is the process stable, can "correctly processed" be defined, is there an owner in Operations to drive rollout.

• Build production agents with AI. Take a use case from prototype to a deployed, audited agent, leaning heavily on agentic coding tools to move quickly: handling messy real-world inputs (PDFs, scans, voice), encoding complex domain rules, and integrating with the customer's systems.

• Translate between worlds. Explain the same system two ways: a technical view for the client's engineers and a clear, outcome-focused view for their product and business teams. Often in German.

• Ship through our products. Use elluminate to evaluate agents with evidence before go-live, ellarun to deploy them securely with full audit trails, and ellaverse to validate them against realistic, domain-specific scenarios.

• Close the loop. Bring what you learn in the field back to the product and research teams, so each engagement makes the next one faster.

Must-haves

• A builder's mentality
  , whatever your background. We don't care what you studied. CS, business, physics, biology, economics, something else entirely, or nothing t matters is that you're a builder: smart, driven, hungry, and happiest when you're shipping something real. If you have that mentality and you're great with AI agents, the rest is learnable.

• Willingness to work side-by-side with clients
  , on-site in Germany and across Europe. These embeds are time-boxed rather than permanent, but during an engagement you should expect to be physically with the customer where the work demands it.

• You're excellent at understanding unfamiliar systems quickly
  , reading a codebase or environment and figuring out what it does, why, and where the risks are, even if you didn't write it and wouldn't have written it that way.

• You're fluent with AI coding agents (Claude Code, Codex, Cursor, or similar) and use them as your default way of working. You don't need to be a rockstar coder; you need to be excellent at directing agents to build, debug, and ship.

• You're a strong communicator who can explain the same system to two very different audiences: deep and technical for engineers, clear and outcome-focused for product and business stakeholders.

• Comfort working directly with customers: scoping problems, managing expectations, and translating between domain experts and engineering.

• Enthusiasm about AI and its applications. In software development and beyond.

• On-site collaboration ≥3 days/week in Berlin or Bremen. Travel to our Bremen HQ during onboarding.

• Fluent,
  professional German
  . You'll run workshops, present to client engineers and business stakeholders, and write client-facing material in German.

• Fluency in English.

• Valid EU work authorization.

Nice-to-haves

• Experience in regulated industries (insurance, banking, public sector) or other domains with heavy compliance and audit requirements.

• Hands-on experience with LLMs, agent frameworks, agent evaluation, RL environments.

• Experience taking AI from prototype to production, not just demos.

• Open-source…