AI Engineer

Job Summary

Owning the AI core of a new product, the full-time AI Engineer will design and manage the inference pipeline, prompt versioning, and cost telemetry while working remotely with a focused team to deliver a production system that continuously improves for thousands of users.

Key responsibilities

• Design and run the inference pipeline, including retrieval-augmented generation and model routing
• Own prompt versioning and the evaluation suite, ensuring real evaluations and release readiness
• Implement cost telemetry and maintain cost discipline to ensure product profitability at scale

Required qualifications

• Experience shipping at least one production LLM-powered product or feature with detailed knowledge of prompts, evaluations, and cost telemetry
• Ability to recover from issues such as prompt drift, model version regression, and evaluation failures
• Strong full-stack engineering skills, proficient in Python or TypeScript, and familiar with Postgres and SQL
• Experience with vector stores (pgvector, Pinecone, or equivalent)
• Hands-on experience with Anthropic API preferred; OpenAI API experience is also acceptable