Model Operations Lead, AI Gateway

What you'll do

• Hire, coach, and lead the models team to manage the AI Gateway catalog and intelligence.
• Execute end-to-end model launches including provider integrations, capability testing, pricing, and security reviews.
• Maintain catalog accuracy by identifying silent regressions in tool calling, pricing, and model behavior.
• Develop model intelligence through evals, capability maps, and per-task rankings for auto-routing profiles.
• Manage the product roadmap for the catalog based on usage, quality, reliability, and cost data.
• Automate repeatable tasks like endpoint validation, eval runs, and pricing reconciliation using scripts and agent workflows.
• Coordinate with Engineering, Product, and Partnerships stakeholders to align on project status and blockers.
• Write code and debug using terminal tools to support hands-on technical requirements and failed launch investigations.

What we're looking for

• Experience hiring, managing, and growing engineers or operators while providing direct feedback and delegating ownership (preferred).
• Proven track record of taking technical launches or integrations from ambiguity to production across teams and partners (preferred).
• Hands-on ability to write TypeScript, Python, or Rust, read API docs, and debug using terminal tools (preferred).
• Deep familiarity with new models, inference providers, streaming, tool calling, and provider-specific model behaviors (preferred).
• Data-driven product instincts and an SRE approach to defining and alerting on service health (preferred).
• Daily experience building with agents, including scoping work and verifying outputs (preferred).
• Experience at an inference provider, model lab, model router, eval platform, or API company (preferred).
• Export control laws, including the U.S. Export Administration Regulations.