• Build eval harnesses and benchmarks that use tracked pricing outcomes as ground truth for model quality.
• Systematize and automate expert review workflows that are 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 managed by hand.
• Own LLM routing across providers (Anthropic, Google, and others) with explicit cost, latency, and quality tradeoffs.
• Maintain infrastructure and data residency boundaries, such as ensuring EU model calls remain within the EU.
• Extend the MCP server used by LLM agents so that features are agent-driven, not just UI-driven.
• Work within a typed ontology of pricing entities to keep model outputs structured and auditable.
• Identify and remediate systemic latency, data drift, and cold-start issues in the pricing loop.
• 
  

What We're Looking For

• 8 or more years of engineering experience with strong, recent, production-grade LLM depth.
• Proven track record shipping and owning LLM-powered product features end-to-end, from development through production monitoring.
• Hands-on experience building eval harnesses and observability for LLM systems, including baselining prompts against a typed ontology for release gating.
• Experience owning LLM infrastructure and routing across multiple models with explicit cost, latency, and quality tradeoffs.
• Comfort working with structured data models and typed ontologies (for example, Pydantic models for pricing entities) to ensure auditable outputs.
• Familiarity with MCP or building tools for LLM agents, and platforms such as LangChain, LlamaIndex, Braintrust, or OpenRouter.
• Experience operating under data residency, SOC2, and GDPR constraints, ideally in pricing, billing, or payments domains.
• Strong ability to communicate about non-deterministic systems clearly to clients and non-technical stakeholders.
• Must be authorized to work in the United States. Visa sponsorship is not available.
•