Model Operations Lead, AI Gateway
About The Position
Cloudflare is hiring a people-management lead for the models team within AI Gateway. AI Gateway provides developers with access to models from multiple providers, with reliability, observability, security, cost controls, and routing. The role will lead the operations behind the model catalog—including provider integrations, capability testing, pricing and metering, capacity, security reviews, documentation, health, and deprecations—and build model intelligence that helps developers select and route requests to appropriate models. The lead will hire, develop, and manage the team while remaining hands-on, writing code, building agent-driven workflows, and investigating launch failures or evaluation issues. The role owns model launches end-to-end, catalog accuracy and reliability, model evaluations and rankings, auto-routing profiles, and operational automation. It also treats the catalog and model intelligence as products, using usage, quality, reliability, and cost data to guide what is offered and inform the roadmap. This position reports to the AI Gateway Engineering Manager. Available locations are Austin, Texas; New York City, New York; and San Francisco, California.
Requirements
- Experience hiring, managing, and developing engineers or operators, including providing direct feedback, delegating ownership, and expanding team scope without becoming a bottleneck.
- A proven track record of taking technical launches or integrations from ambiguity to production across teams and partners.
- Hands-on ability to write TypeScript, Python, or Rust; read API documentation; inspect endpoints; and debug with terminal tools such as logs and cURL.
- Deep familiarity with new models, model labs, and inference providers.
- Hands-on understanding of streaming, tool calling, structured outputs, rate limits, token pricing, and provider-specific variations in model behavior.
- Data-driven product instincts for advocating to add, modify, or retire catalog items.
- An SRE approach to defining, measuring, and alerting on service health, managing incidents, and fixing root causes.
- Daily experience building with agents, including scoping work, verifying outputs, and appropriately combining deterministic checks with human judgment.
- Meticulous attention to model IDs, context limits, per-token prices, and response fields.
Nice To Haves
- Experience at an inference provider, model lab, model router, evaluation platform, or API company.
- Background in evaluations, ranking or recommendation systems, observability, metering, or usage-based billing.
- Familiarity with Cloudflare Workers, AI Gateway, Workers AI, or Replicate.
- Relevant background in engineering management, SRE, partner engineering, evaluations or applied machine learning, technical program management, or solutions engineering.
Responsibilities
- Hire, coach, develop, and lead the models team, providing direct feedback, meaningful ownership, and opportunities for team members to grow into leadership roles.
- Lead model launches end-to-end, coordinating integrations, testing, evaluations, pricing, metering, capacity, security reviews, documentation, and announcements.
- Prepare day-zero launches so models can be made available quickly, with tested capabilities, accurate pricing and documentation, and a clear decision about routing eligibility.
- Maintain an accurate and reliable model catalog, ensuring published capabilities, limits, versions, and prices match actual provider behavior.
- Detect silent model or provider regressions, including issues with tool calling, streaming, quantization, usage, and pricing, before they affect customers.
- Own evaluations, capability maps, and per-task rankings that support auto-routing profiles and model recommendations; ensure they are methodologically sound and connect detected regressions to routing decisions.
- Make product decisions about which models, routing profiles, and market intelligence to offer, grounded in usage, quality, reliability, and cost data, and translate findings into roadmap input.
- Establish a lightweight operating cadence and source of truth for work in flight, ownership, blockers, and upcoming launches, keeping stakeholders aligned without relying on status meetings.
- Set clear expectations with providers and coordinate with Engineering, Product, Partnerships, and other stakeholders.
- Build scripts, tools, and agent workflows to automate endpoint validation, evaluation runs, catalog and pricing reconciliation, regression detection, and provider follow-ups, reducing manual effort per launch.
- Deliver auto-routing that measurably improves cost or quality compared with a fixed model choice.
- Define, measure, and monitor model and provider health, manage incidents calmly, and address root causes.
Benefits
- Medical/Rx insurance
- Dental insurance
- Vision insurance
- Flexible spending accounts
- Commuter spending accounts
- Fertility and family-forming benefits
- On-demand mental health support and Employee Assistance Program
- Global travel medical insurance
- Short- and long-term disability insurance
- Life and accident insurance
- 401(k) retirement savings plan
- Employee stock participation plan
- Flexible paid time off covering vacation and sick leave
- Leave programs, including parental, pregnancy health, medical, and bereavement leave
- Equity plan participation
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Manager
Education Level
No Education Listed
