Founding AI Engineer

Mondrio is hiring a Founding AI Engineer to build the evaluation systems, feedback loops, and LLM infrastructure that let our pricing AI earn trust and drive measurable revenue impact; you'll join a small, product-focused team shipping to customers and owning outcomes. This role matters because its work directly ties model outputs to revenue and compliance constraints in high-stakes B2B pricing decisions.

What youll do

• Build eval harnesses and benchmarks that use tracked pricing outcomes as ground truth.
• Systematize and automate expert review workflows currently done manually.
• Develop AI personas that simulate B2B buying committees and behavioral effects using usage data and call transcripts.
• Automate persona training pipelines that are today manual.
• Own LLM routing across providers (Anthropic, Google, etc.) with explicit cost, latency, and quality tradeoffs.
• Maintain infrastructure and data residency boundaries (e.g., ensure EU model calls remain in the EU).
• Extend the MCP server used by LLM agents, including customer agents, so features are agent-driven.
• Ensure features are considered done when agents can drive them through MCP, not just when UI renders.
• Work within a typed ontology of pricing entities so model outputs are structured and auditable.
• Identify and remediate systemic latency, data drift, and cold-start issues in the pricing loop.

What Mondrio is looking for

• 8+ years of engineering experience with strong, recent production LLM depth.
• Proven track record shipping and owning LLM-powered product features in production.
• Direct experience building evals and observability for LLM systems (not just running dashboards).
• Experience with MCP or building tools for LLM agents and familiarity with platforms like LangChain, LlamaIndex, Braintrust, or OpenRouter.
• Experience operating under data residency, SOC2, and GDPR constraints in domains where correctness is audited (pricing, billing, payments).
• Strong communication skills to explain non-deterministic systems to clients and partners and product-engineer instincts to scope and deliver pragmatic solutions.
• Authorized to work in the US (Mondrio is unable to sponsor visas at this time).