Model Operations Lead (AI Gateway)

Location: In-office in Austin, TX; New York City, NY; or San Francisco, CA.

Salary: $230,000–$317,000 annual for Bay Area hires; $275,000–$303,000 annual for hires based in New York City, New Jersey, Washington, Washington DC, or California excluding the Bay Area.

Company

hirify.global operates a large global network that protects and accelerates Internet applications and provides infrastructure, security, and AI-related products.

What you will do

• Build, hire, coach, and lead the models team while developing leads and establishing clear ownership.
• Run model launches end-to-end, including provider integrations, capability testing, evaluations, pricing, metering, capacity, security reviews, documentation, and routing eligibility.
• Maintain catalog accuracy and health by detecting regressions in tool calling, streaming, quantization, usage, pricing, and provider performance.
• Build model intelligence through evaluations, capability maps, per-task rankings, recommendations, and auto-routing profiles.
• Align Engineering, Product, Partnerships, providers, and other stakeholders through a lightweight operating cadence.
• Automate endpoint validation, evaluation runs, catalog and pricing reconciliation, regression detection, and provider follow-ups using scripts, tools, and agent workflows.

Requirements

• Experience hiring, managing, and growing engineers or operators, giving direct feedback, delegating ownership, and expanding team scope.
• Proven experience 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, logs, and cURL.
• Deep familiarity with new models, model labs, and inference providers, including streaming, tool calling, structured outputs, rate limits, token pricing, and provider-specific behavior.
• Data-driven product judgment for adding, modifying, or retiring catalog items, combined with an SRE approach to service health, alerting, incident management, and root-cause fixes.
• Daily experience building with agents, verifying outputs, and integrating deterministic checks or human judgment.
• Meticulous attention to model IDs, context limits, per-token prices, and response fields.

Nice to have

• 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 hirify.global Workers, AI Gateway, Workers AI, or Replicate.
• Background in engineering management, SRE, partner engineering, evaluations or applied ML, technical program management, or solutions engineering.

Culture & Benefits

• In-office work at one of the listed United States locations.
• Medical, dental, vision, flexible spending, commuter, fertility and family-forming benefits.
• Mental health support, employee assistance, global travel medical insurance, disability insurance, and life and accident insurance.
• 401(k), employee stock participation plan, equity plan eligibility, and flexible paid time off covering vacation and sick leave.
• Parental, pregnancy health, medical, and bereavement leave programs.

Hiring process

• Candidates progressing to the offer stage may be asked to attend an in-person interview at a hirify.global office or hub.
• The position may require authorization to receive technology controlled under U.S. export laws without sponsorship for an export license.