AI Platform Engineer

As an AI Platform Engineer at Polygon Labs, you build the platform that powers every agent across the company. You join a small, flat Platform Team owning the entire AI platform-agent runtime, MCP servers, guardrails, evaluations, observability, and spend tracking. This is a hands-on role where you write code, ship to production, and take ownership of your deliverables while working with domain experts (Operators) who manage fleets of agents across engineering, business development, compliance, support, and finance.

What you'll do

• Move agentic workflows into production, taking prototypes to robust systems for real users 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, authentication (per-user OAuth), and maintaining a clean connector inventory for Slack, GitHub, Jira, HubSpot, and internal services.
• Develop autonomous agents that act and plan across tools through trust stages: shadow, suggest, execute, and autonomous.
• Embed guardrails into the platform, providing each agent its own identity, scoped credentials, audit logs, CI checks, approval gates, allowlists, and least-privilege access.
• Build evaluation frameworks (test sets, regression suites, live scoring in production) so every agent releases with quality metrics tied to business outcomes.
• Instrument agents for observability: tracing, logging, latency, cost, drift detection, and daily dashboards for Operators.
• Track AI spend across providers (Anthropic, OpenAI, OpenRouter), setting budgets, alerts, and spend attribution to teams, agents, and workflows.
• Support Operators by developing features from their requests, writing documentation, running enablement sessions, and building self-service tools.
• Create skills and plugins centralizing company knowledge (processes, standards, security, brand), versioning and reviewing these to ensure consistent, repeatable agent output.
• Proactively find and automate manual, repetitive processes across the company, measuring outcomes and iterating rapidly.

What you bring

• 5+ years as a software, platform, or infrastructure engineer, including experience prior to AI coding tools, with a solid grasp of system design, data modeling, testing, debugging, and code review.
• 6-12 months shipping LLM-based systems to production, with agentic workflows in use by real end users.
• Daily, hands-on experience with AI coding agents like Claude Code and Codex to write, test, and review production code.
• 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 like 1Password).
• Experience designing guardrails: least-privilege, 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 system observability: tracing, metrics, alerting, dashboards (OpenTelemetry, Grafana, Datadog, Langfuse, LangSmith, Braintrust).
• Experience tracking AI spend across vendors: per-key limits, cost centers, budgets, actionable alerts.
• Strong proficiency in at least one of TypeScript, Python, or Go; working knowledge of CI/CD (GitHub Actions or similar) and cloud infrastructure.
• A track record of independently identifying and automating manual processes (with two or three concrete examples).
• Clear, concise written communication (specs, runbooks, RFCs).

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): key management, routing, fallback.
• Experience extending open-source coding agents (OpenCode, Pi).
• Awareness of emerging agent identity standards (MCP enterprise-managed auth, Okta Cross App Access).
• Context/retrieval engineering: vector stores, agent memory, permissioned retrievals.
• ML engineering: model evaluation, fine-tuning, model routing.
• Experience with agent runtimes/sandboxes (Modal, n8n, containerized environments).
• Public technical work: open-source tools, servers, blog posts, talks about agent production experience.

What we offer

• Remote first global workforce
• Industry leading Medical, Dental and Vision health insurance (in certain countries fully covered for employees and their dependents)
• Company matching 401k with 3% match (United States employees only)
• $1,500 Home Office Set Up Allowance (lifetime 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

About Polygon Labs

Polygon Labs is a global blockchain payments company building infrastructure to move money instantly, reliably, and at internet scale. It operates the Polygon Open Money Stack, an integrated set of services and technologies for on-chain value transfer, and has facilitated trillions of dollars in on-chain transactions for some of the globe's largest banks, fintechs, enterprises, and consumer applications.