AI Platform Engineer
New
P
Polygon LabsAI platform
Location: EMEA - Remote; Secondary Locations: USA - RemoteFull-TimeSenior
Salary$1,500 Home Office Set Up Allowance (life-time max)
Apply NowOpens the employer's application page
Job Details
- Experience
- 5+ years as a software, platform, or infrastructure engineer; 6-12 months shipping LLM-based systems to production
- Required Skills
- PythonOAuthTypeScriptGoCI/CD
Requirements
- Have 5+ years of experience as a software, platform, or infrastructure engineer, including experience before AI coding tools.
- Have 6-12 months of experience shipping LLM-based systems to production with agentic workflows used by real end users.
- Use AI coding agents such as Claude Code and Codex hands-on to write, test, and review production code.
- Have experience building autonomous or multi-step agents with tool use, using Claude Agent SDK, Anthropic/OpenAI APIs, or similar.
- Have MCP server experience, including OAuth flows, scoped tokens, and user-level access control.
- Have identity and access experience with Okta or a similar identity provider, SSO (SAML/OIDC), SCIM provisioning, and group-based and device policies.
- Have experience creating automated system identities, such as GitHub Apps, service accounts, API keys, and secrets managed with tools like 1Password.
- Be able to design guardrails including least-privilege access, audit logs, CI checks, approval gates, allowlists, and policy-as-code.
- Have experience creating LLM evaluations, including test sets, rubrics, CI regression, release gates, and live production scoring.
- Have experience instrumenting production observability with tracing, metrics, alerting, and dashboards; listed tools include OpenTelemetry, Grafana, Datadog, Langfuse, LangSmith, and Braintrust.
- Be strong in at least one of TypeScript, Python, or Go, with working knowledge of CI/CD and cloud infrastructure.
- Have a track record of independently identifying and automating manual processes, with two or three concrete examples.
- Be able to write clear, concise specs, runbooks, and RFCs.
Responsibilities
- Move agentic workflows from prototypes into robust production systems with SLAs.
- Build and manage MCP servers, including system design, hosting, security, authentication, and connector inventory.
- Develop autonomous agents that plan and act across tools through shadow, suggest, execute, and autonomous trust stages.
- Embed agent identities, scoped credentials, audit logs, CI checks, approval gates, allowlists, and least-privilege access into the platform.
- Build evaluation frameworks with test sets, regression suites, and live production scoring.
- Instrument agents for tracing, logging, latency, cost, drift detection, and Operator dashboards.
- Track AI spend across providers, setting budgets, alerts, and spend attribution.
- Develop platform features, documentation, enablement sessions, and self-service tools for Operators.
- Create and maintain versioned skills and plugins that centralize company knowledge.
- Identify and automate repetitive processes across the company, measuring outcomes and iterating.
View Full Description & ApplyYou'll be redirected to the employer's site
