Responsibilities
- Move agentic workflows into production, taking prototypes to robust systems with SLAs, such as spec-to-PR agents, AI code review, incident triage, and KYB review.
- Build and manage MCP servers, including system design, hosting, security, authentication, and connectors for Slack, GitHub, Jira, HubSpot, and internal services.
- Develop autonomous agents that act and plan across tools through shadow, suggest, execute, and autonomous trust stages.
- Build platform guardrails, including 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 production scoring.
- Instrument agents for observability, including tracing, logging, latency, cost, drift detection, and dashboards.
- Track AI spend across providers, setting budgets, alerts, and spend attribution.
- Support Operators by developing requested features, writing documentation, running enablement sessions, and building self-service tools.
- Create, version, and review skills and plugins that centralize company knowledge.
- Identify and automate manual, repetitive processes, measuring outcomes and iterating.
Requirements
- 5+ years as a software, platform, or infrastructure engineer, including experience before AI coding tools; solid system design, data modeling, testing, debugging, and code review skills.
- 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.
- MCP server experience, including OAuth flows, scoped tokens, and user-level access control.
- Identity and access experience with Okta or similar IdP, SSO (SAML/OIDC), SCIM provisioning, group-based and device policies.
- Experience creating automated system identities, such as GitHub Apps and service accounts, and using API keys and secret managers like 1Password.
- Experience designing guardrails, creating LLM evaluations, and instrumenting production system observability.
- Experience tracking AI spend across vendors.
- Strong skills in at least one of TypeScript, Python, or Go; working knowledge of CI/CD and cloud infrastructure.
- Track record of independently identifying and automating manual processes, with two or three concrete examples.
- Clear, concise written communication, including specs, runbooks, and RFCs.