Founding AI Engineer

Join a small, high-velocity team building an AI-powered pricing platform that helps B2B companies continuously optimize their pricing strategy and improve deal outcomes. The AI recommends prices; expert Pricing Architects stay in the loop on high-stakes calls. Your mandate is to build the evaluation systems and feedback loops that let the AI earn more of that trust over time. This is applied AI on a problem where quality is directly measurable in customer revenue. What You’ll Do Design and build eval harnesses and benchmarks that use tracked pricing outcomes as ground truth for AI recommendations. Own LLM infrastructure and model routing across multiple frontier providers (Anthropic, Google) with explicit cost/latency/quality tradeoffs. Maintain EU data-residency boundaries for EU customer model calls, ensuring compliance with applicable data regulations. Extend an MCP server so LLM agents - including customers’ own agents - can programmatically drive the platform. Build observability and feedback loops that surface where the AI earns or loses trust from human reviewers. Bridge non-deterministic engineering concepts clearly to less technical stakeholders (sales, customer success, leadership).

8+ years of software engineering experience with strong, recent production LLM depth. Demonstrated track record of shipping and owning LLM-powered product features in production - not research-only work. Has personally built evals and observability for LLM systems (not just consumed someone else’s dashboard). Comfortable operating across the full stack: TypeScript/Python, FastAPI, GCP, and modern LLM tooling. Strong communicator who can make non-deterministic engineering concepts legible to non-technical stakeholders. Nice to Have Experience with MCP or building tools/integrations for LLM agents. Familiarity with LangChain, LlamaIndex, Braintrust, Langfuse, or OpenRouter. Background in a domain where correctness is audited - pricing, billing, payments, or similar. Experience at a seed-stage or founding-team environment; comfort with AI-assisted coding workflows (e.g., Cursor, Claude Code). Tech Stack Languages & Frameworks: TypeScript, React, Python, FastAPI Infrastructure: GCP, Pulumi, Cloudflare Pages, MongoDB Atlas AI/LLM Tooling: FastMCP, Langfuse, Anthropic Claude, Google Gemini, This is a fully on-site role based in Amsterdam, Netherlands. Candidates must be able to work on-site; remote work is not available for this position.