Founding AI Engineer
Core
Build evaluation systems, feedback loops, and LLM infrastructure for an AI-powered B2B pricing platform to optimize pricing strategies and drive revenue.
Role type
Founding AI Engineer (LLM Infrastructure & Evaluation)
Builds
AI-powered pricing platform features, LLM agents, and evaluation harnesses for B2B clients.
Domain
B2B SaaS, Pricing Strategy, Large Language Models
Deliverable
production ML models
Required skills
Production LLM engineering, LLM evaluation & observability, MCP server development, LLM agent tooling, Multi-provider LLM routing, Data residency compliance, Structured output design, Latency & drift optimization
Preferred skills
AI pricing recommendation harnesses, SaaS pricing domain expertise
Technologies
Anthropic, Google, LangChain, LlamaIndex, Braintrust, OpenRouter, MCP
Responsibilities
Build eval harnesses using tracked pricing outcomes; Automate expert review workflows; Develop AI personas simulating B2B buying committees; Own LLM routing across providers with cost/latency/quality tradeoffs; Maintain infrastructure and data residency boundaries; Extend MCP server for LLM agents; Remediate systemic latency, data drift, and cold-start issues.
Seniority
Founding team, high-ownership IC
