Founding AI Engineer role at an early-stage B2B SaaS pricing intelligence startup based in San Francisco, California, United States. You will be among the first engineers on a small, product-focused team, helping shape the technical direction of an AI-powered pricing platform used in high-stakes B2B deals. You will design and build eval harnesses and benchmarks that use tracked pricing outcomes as ground truth, automate expert-review workflows, develop AI personas that simulate B2B buying committees, and automate persona training pipelines. You will own LLM routing across providers (e.g., Anthropic, Google) with explicit cost, latency, and quality tradeoffs, maintain infrastructure and data residency boundaries (SOC2/GDPR compliance), extend the MCP server for agent-driven features, and work within a typed ontology of pricing entities to ensure outputs are structured and auditable. You will address systemic latency, data drift, and cold-start issues in the pricing loop. Requirements include 8+ years of production LLM depth, authorization to work in the United States (visa sponsorship not available), experience with evals and observability for LLM systems, ownership of LLM infrastructure, proficiency with typed data models (e.g., Pydantic), end-to-end ownership of LLM-powered features, and strong communication skills. Nice-to-haves include experience with MCP, LangChain, LlamaIndex, OpenRouter, and familiarity with data residency/compliance controls (SOC2, GDPR). Salary: $225,000–$255,000 USD annually; founding-team equity. Location: On-site in San Francisco, California, Uni

Founding AI Engineer role at an early-stage B2B SaaS pricing intelligence startup based in San Francisco, California, United States. You will be among the first engineers on a small, product-focused team, helping shape the technical direction of an AI-powered pricing platform used in high-stakes B2B deals. You will design and build eval harnesses and benchmarks that use tracked pricing outcomes as ground truth, automate expert-review workflows, develop AI personas that simulate B2B buying committees, and automate persona training pipelines. You will own LLM routing across providers (e.g., Anthropic, Google) with explicit cost, latency, and quality tradeoffs, maintain infrastructure and data residency boundaries (SOC2/GDPR compliance), extend the MCP server for agent-driven features, and work within a typed ontology of pricing entities to ensure outputs are structured and auditable. You will address systemic latency, data drift, and cold-start issues in the pricing loop. Requirements include 8+ years of production LLM depth, authorization to work in the United States (visa sponsorship not available), experience with evals and observability for LLM systems, ownership of LLM infrastructure, proficiency with typed data models (e.g., Pydantic), end-to-end ownership of LLM-powered features, and strong communication skills. Nice-to-haves include experience with MCP, LangChain, LlamaIndex, OpenRouter, and familiarity with data residency/compliance controls (SOC2, GDPR). Salary: $225,000–$255,000 USD annually; founding-team equity. Location: On-site in San Francisco, California, Uni