Founding AI Engineer
$225,000–$255,000 year
On-siteSan Francisco, California, United States
Job Summary
Build eval harnesses and benchmarks using tracked pricing outcomes as ground truth, then systematize and automate expert review workflows currently done manually. Develop AI personas that simulate B2B buying committees using usage data and call transcripts, while automating their training pipelines. Own LLM routing across providers with explicit cost, latency, and quality tradeoffs, and maintain infrastructure and data residency boundaries. Extend the MCP server used by LLM agents so features are agent-driven, ensuring model outputs remain structured and auditable within a typed ontology. Identify and remediate systemic latency, data drift, and cold-start issues in the pricing loop. This high-ownership founding role requires 8+ years of production LLM engineering experience, with on-site work in San Francisco, CA.
Required Qualifications
- 8+ years of engineering experience with strong, recent production LLM depth
- Proven track record shipping and owning LLM-powered product features in production — not just dashboards or research prototypes
- Direct hands-on experience building evals and observability for LLM systems
- Experience with MCP or building tools/integrations for LLM agents
- Familiarity with platforms such as LangChain, LlamaIndex, Braintrust, or OpenRouter
- Experience operating under data residency, SOC 2, and GDPR constraints in domains where correctness is audited (pricing, billing, payments, or similar)
- Strong communication skills — able to explain non-deterministic systems clearly to clients, partners, and pricing experts
- Product-engineer instincts: able to scope pragmatic solutions and deliver under ambiguity in a lean startup environment
- Authorized to work in the US
- Visa sponsorship is not available for this role
- This role is on-site in San Francisco, CA
- Candidates should be based in or willing to relocate to the San Francisco Bay Area
Desired Qualifications
- Experience building evaluation harnesses specifically for AI pricing recommendations using historical pricing outcomes as ground truth
- Background in SaaS pricing, revenue operations, or a high-stakes revenue-impact domain
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.