Forward Deployed Engineer, R&D AI Automation

About the role

Hands‑on engineer in the R&D team building AI agents that control web browsers with open‑weight LLMs. You will work directly with domain experts who operate legacy web applications, observe their workflows and turn them into structured specifications for training and testing.

Key responsibilities

• Observe and record how domain experts operate their applications, and elicit hidden details.
• Decompose workflows into explicit structures: states, decisions, exceptions and failure modes, generalized across applications.
• Transform those structures into artefacts such as evaluation tasks, fault specifications for simulated apps, and demonstration recordings.
• Run the feedback loop from real applications to the R&D team, building quick prototypes and demos.

Required profile

• Has worked embedded with expert users on behalf of an engineering or research team and can articulate undocumented processes.
• Has turned messy, undocumented human processes into specifications that held in production.
• Has built evaluation tasks or simulated environments from real workflows.
• Patient and precise with non‑technical experts; runs discovery sessions effectively.
• Builds working prototypes in days using TypeScript or Python and browser automation tools like Playwright.

Required skills

• Playwright
• Chrome DevTools Protocol
• TypeScript
• Python
• Kubernetes
• vLLM
• SGLang
• OpenHands
• LangGraph
• smolagents
• rrweb
• HAR / WARC
• Gherkin
• LLM‑as‑judge
• Langfuse

What we offer

• Founding‑team scope with high impact.
• AI‑augmented engineering environment.
• Access to on‑premise Nvidia B200 GPUs.
• Flexible work environment.