AI Platform Engineer

Skills

About the Role

You will help build the platform that powers every agent at the company. You will move agentic workflows into production, build and manage MCP servers, develop autonomous agents, embed guardrails, build evaluation frameworks, instrument agents for observability, and track AI spend across providers. You will also support internal Operators with features, documentation, enablement sessions and self-service tools, create reusable skills and plugins, and proactively automate manual processes. This is a hands-on individual contributor role where you write code, ship to production and own your deliverables.

Requirements

• 5+ years as a software, platform, or infrastructure engineer, including experience prior to AI coding tools
• 6-12 months shipping LLM-based systems to production
• Daily hands-on experience with AI coding agents like Claude Code and Codex
• Experience building autonomous or multi-step agents with tool use
• MCP server experience (OAuth flows, scoped tokens, user-level access control)
• Identity and access experience: Okta, SSO (SAML/OIDC), SCIM provisioning
• Creating automated system identities (GitHub Apps, service accounts, API keys, secret managers)
• Designing guardrails: least-privilege, audit logs, CI checks, approval gates, allowlists, policy-as-code
• Creating evals for LLM systems
• Instrumenting production observability (OpenTelemetry, Grafana, Datadog, Langfuse, LangSmith, Braintrust)
• Tracking AI spend across vendors
• Strong in at least one of TypeScript, Python, Go; working knowledge of CI/CD and cloud infrastructure
• Track record of independently identifying and automating manual processes
• Clear, concise written communication

Responsibilities

• Move agentic workflows into production with SLAs
• Build and manage MCP servers including design, hosting, security and authentication
• Develop autonomous agents that act and plan across tools through trust stages
• Embed guardrails into the platform including identity, scoped credentials, audit logs, CI checks, approval gates and allowlists
• Build evaluation frameworks with test sets, regression suites and live scoring
• Instrument agents for observability including tracing, logging, latency, cost and drift detection
• Track AI spend across providers with budgets, alerts and attribution
• Support Operators with features, documentation, enablement sessions and self-service tools
• Create and version skills and plugins centralizing company knowledge
• Proactively find and automate manual, repetitive processes

Benefits

• Remote first global workforce
• Medical, Dental and Vision health insurance
• Company matching 401k with 3% match (US only)
• $1,500 Home Office Set Up Allowance (life-time max)
• $200 Annual Book Allowance Program
• $75 Monthly internet or phone reimbursement
• Flexible Time Off
• Company issued laptop
• Egg freezing, mental health, and employee wellness benefits