Software Engineer - AI Tooling Infrastructure

About the role

A partner company is looking for an experienced Software Engineer to build, operate and scale the backend infrastructure behind AI-driven developer tools, including AI agents, developer assistants and Model Context Protocol (MCP) integrations. The role focuses on reliability, security, performance and observability in an environment where AI traffic brings unique infrastructure challenges. It is fully remote, with an asynchronous, globally distributed team.

Key responsibilities

• Build, deploy, operate and scale production backend services, including MCP servers, agent skills and AI assistants
• Own service architecture and infrastructure decisions, and improve reliability, maintainability, scalability and deployment processes
• Define and monitor SLOs, track error budgets and work with SRE teams on reliability improvements
• Take part in on-call rotations, investigate incidents, write runbooks and preventive solutions
• Manage operational support requests and identify recurring issues
• Design and maintain authentication and authorization for AI agents and machine clients, including OAuth and scoped tokens
• Set up observability with metrics, distributed tracing, logging, dashboards and alerting
• Manage AI agent traffic with rate limits, capacity controls and safeguards against traffic spikes
• Collaborate with Platform, SRE, Authentication, Billing and Edge Functions teams

Required profile

• At least 5 years of experience building, deploying and operating production backend services, including on-call participation
• Proven experience designing and maintaining APIs, including versioning, error handling, rate limiting and backward compatibility
• Strong understanding of OAuth, OIDC, JWT and API authorization
• Good knowledge of PostgreSQL and relational databases
• Experience with CI/CD pipelines, Docker and Infrastructure as Code
• Ability to troubleshoot distributed systems with metrics, logs and traces
• Deep expertise in at least one of: APIs and authentication, production operations, or gateways and distributed systems

Nice to have

• Experience with AI agent tooling, MCP or infrastructure serving AI agents and LLM clients
• Familiarity with Grafana, OpenTelemetry or Logflare and practical SLO implementation
• Open-source contributions, especially in Node.js, Go, TypeScript or API tooling

What we offer

• Fully remote work with no office attendance requirement
• WeWork membership or co-working budget
• Employee stock option plan (ESOP)
• Technology allowance for laptops, monitors and headphones
• Health insurance for employees and 80% for dependents
• Annual off-site and flexible, asynchronous working arrangements
• Annual learning and education allowance