AI Platform Engineer

The role

You will help build the platform that runs every AI agent at Polygon Labs. You will write code, ship agent systems to production, and own your work after release.

What you will do

• Move agentic workflows into production with SLAs (for example spec-to-PR agents, AI code review, incident triage, KYB review).
• Build and manage MCP servers, including system design, hosting, security and per-user OAuth authentication.
• Develop autonomous agents that act and plan across tools through the stages shadow, suggest, execute and autonomous.
• Embed guardrails into the platform: agent identities, scoped credentials, audit logs, CI checks, approval gates, allowlists and least-privilege access.
• Build evaluation frameworks with test sets, regression suites and live scoring in production.
• Instrument agents for observability: tracing, logging, latency, cost, drift detection and daily dashboards.
• Track AI spend across providers (Anthropic, OpenAI, OpenRouter), setting budgets, alerts and spend attribution.
• Support Operators by building features from their requests, writing documentation, running enablement sessions and building self-service tools.
• Create and version skills and plugins that hold company knowledge for consistent agent output.
• Find and automate manual, repetitive processes across the company, measuring outcomes and iterating quickly.

Required qualifications

• 5+ years as a software, platform or infrastructure engineer, including experience before AI coding tools.
• 6-12 months shipping LLM-based systems to production, with agentic workflows used by real end users.
• Daily hands-on experience with AI coding agents such as Claude Code and Codex.
• Experience building autonomous or multi-step agents with tool use (Claude Agent SDK, Anthropic/OpenAI APIs or similar).
• MCP server experience, including OAuth flows, scoped tokens and user-level access control.
• Identity and access experience: Okta (or similar IdP), SSO (SAML/OIDC), SCIM provisioning, group-based and device policies.
• Experience creating automated system identities (GitHub Apps, service accounts, API keys, secret managers such as 1Password).
• Experience designing guardrails: least-privilege access, audit logs, CI checks, approval gates, allowlists and policy-as-code.
• Experience creating evals for LLM systems: test sets, rubrics, CI regression, release gates and live production scoring.
• Experience instrumenting production observability (OpenTelemetry, Grafana, Datadog, Langfuse, LangSmith, Braintrust).
• Experience tracking AI spend across vendors: per-key limits, cost centers, budgets and alerts.
• Strong in at least one of TypeScript, Python or Go; working knowledge of CI/CD (GitHub Actions or similar) and cloud infrastructure.

Nice to have

• Cryptocurrency, blockchain, payments or fintech experience; regulated industry or audit experience is a plus.
• Experience writing agent skills, plugins or shared prompt libraries for organizational reuse.
• Familiarity with model gateways (OpenRouter, LiteLLM, Portkey) for key management, routing and fallback.
• Experience extending open-source coding agents (OpenCode, Pi).
• Awareness of emerging agent identity standards (MCP enterprise-managed auth, Okta Cross App Access).
• Context and retrieval engineering: vector stores, agent memory and permissioned retrievals.
• ML engineering: model evaluation, fine-tuning and model routing.
• Experience with agent runtimes or sandboxes (Modal, n8n, containerized environments).
• Public technical work: open-source tools, servers, blog posts or talks about agents in production.

Benefits

• Remote first global workforce
• Medical, dental and vision health insurance (fully covered in certain countries; country and plan specific)
• 401k with 3% company match (United States employees only)
• $1,500 home office set-up allowance (lifetime max)
• $200 annual book allowance
• $75 monthly internet or phone reimbursement
• Flexible time off
• Company-issued laptop
• Egg freezing, mental health and employee wellness benefits

Before you apply

• The posting says applicants who do not meet every point should still get in touch.
• Accommodations are available throughout the recruitment process.

About the company

Polygon Labs is a global blockchain payments company building infrastructure to move money instantly and reliably. Its stack has supported trillions of dollars in onchain value transfer for banks, fintechs and enterprises.