Software Engineer, Platform (AI Infrastructure)

Location: San Francisco, United States; hybrid with a minimum of 3 days per week onsite. Fully remote candidates will only be considered with a very strong endorsement.

Company

hirify.global develops infrastructure for evaluating how AI models perform in real-world workflows, including online arenas, leaderboards, and model-serving systems.

What you will do

• Build low-latency, high-reliability APIs for leaderboards, models, and arenas.
• Design streaming systems across heterogeneous LLM providers, including partial-failure recovery, mid-stream fallback, and response normalization.
• Develop enterprise infrastructure for rate limiting, authentication, usage metering, cost attribution, audit logging, and SOC 2 compliance.
• Build distributed tracing, latency analysis, token-level usage tracking, and real-time observability dashboards.
• Integrate backend services with the evaluation platform, Arena data, customer benchmarks, Leaderboards, and Evals platforms.
• Work closely with researchers, engineers, and product leadership on zero-to-one and scaling initiatives.

Requirements

• Approximately 5 or more years of backend engineering experience, including substantial work with distributed systems, infrastructure, or developer-facing platforms.
• Strong proficiency in Go; Go is the primary backend language and a must-have requirement.
• Experience with LLM provider APIs such as OpenAI, Anthropic, or Google, including streaming, token management, rate limits, and provider-specific behavior.
• Product-oriented approach to API and developer experience design, with the ability to work effectively in an ambiguous startup environment.
• Availability to work onsite in San Francisco at least 3 days per week; fully remote consideration requires a very strong endorsement.

Nice to have

• Cloud infrastructure experience with AWS, GCP, or Azure, plus Kubernetes, Terraform, Postgres, or Redis.
• Experience building API gateways, proxies, or developer tools such as Bifrost, Kong, Envoy, or Tyk.
• Background in AI/ML infrastructure, model serving, inference, or evaluation frameworks.
• Experience with SSO, RBAC, audit logs, multi-tenancy, or billing systems such as Stripe, Metronome, or Orb.
• Familiarity with vLLM, LiteLLM, LangChain, or other modern AI infrastructure tools.

Culture & Benefits

• Competitive compensation and equity aligned with the market where the employee is permanently based.
• Comprehensive medical, dental, vision, and wellness benefits.
• Opportunity to work on AI infrastructure with a small, mission-driven team.
• Culture focused on transparency, trust, craftsmanship, curiosity, and community impact.