Founding AI Engineer

Role details

ABOUT THE ROLE This is a founding-level AI engineering role at a small, product-focused B2B SaaS pricing platform, sitting at the intersection of LLM infrastructure and high-stakes commercial decisions. You'll own the evaluation systems, feedback loops, and model infrastructure that tie AI-driven pricing recommendations directly to revenue and compliance outcomes. Your work will have immediate, measurable impact on customers from day one. WHAT YOU'LL DO - Build eval harnesses and benchmarks that use tracked pricing outcomes as ground truth for model quality. - Systematize and automate expert review workflows currently handled manually. - Develop AI personas simulating B2B buying committees and behavioral effects using usage data and call transcripts. - Automate persona training pipelines to replace today's manual processes. - Own LLM routing across providers (Anthropic, Google, etc.) with explicit cost, latency, and quality tradeoffs. - Maintain infrastructure and data residency boundaries, ensuring regional model calls comply with applicable regulations. - Extend the MCP server used by LLM agents so that features are driven agent-first, not just UI-first. - Work within a typed ontology of pricing entities to ensure model outputs are structured and auditable. - Identify and remediate systemic latency, data drift, and cold-start issues in the pricing loop. WHAT WE'RE LOOKING FOR - 8+ years of engineering experience with strong, recent production LLM depth. - Proven track record shipping and owning LLM-powered product features end-to-end — from development through production monitoring. - Direct experience building evals and observability for LLM systems, including eval harness creation and prompt baselining against a typed ontology. - Hands-on experience with structured data models (e.g., Pydantic) to produce auditable, typed model outputs. - Experience operating under data residency, SOC 2, and GDPR constraints in domains where correctness is audited (pricing, billing, payments). - Familiarity with LLM tooling platforms such as LangChain, LlamaIndex, Braintrust, or OpenRouter; MCP or LLM agent tooling experience is a plus. - Strong communication skills to explain non-deterministic systems to both technical and non-technical stakeholders. - Ability to thrive in a lean, high-ownership, fast-moving startup environment. - Must be authorized to work in the United States; visa sponsorship is not available. COMPENSATION & BENEFITS Salary range: $225,000 – $255,000 USD annually. Visa sponsorship is not available. LOCATION On-site in Amsterdam, Netherlands.