San Francisco, New YorkFull TimeEngineering
Remotely
llminfrastructureidentity managementobservabilityoktamodel routinginternal platforms
Job Description
📋 Description
- Design and build hosting paths for internal AI apps, bots, and agents
- Develop model routing to select cost/capability-appropriate models with audit trails
- Establish observability, analytics, and per-team cost attribution for AI workloads
- Integrate identity and security patterns (Okta-enabled) for day-one safe workflows
- Collaborate with product AI infra teams to share gateways and telemetry
- Help shape platform strategy and engineering best practices as a pillar founder
🎯 Requirements
- 5+ years in software engineering, with infrastructure/platform/backend focus
- Track record building internal platforms adopted by other teams
- Strong system design for resilient, observable production systems
- Hands-on with LLM ops: model gateways/routing, agent runtimes, evals, cost/usage instruments
- Experience with identity/access management in enterprise (Okta, SSO, service-to-service auth)
🎁 Benefits
- Equity; comprehensive health, dental, vision; retirement contributions
- Parental leave, family planning support; mental health and wellness benefits
- PTO, paid holidays, sick leave, and other leave benefits
- Office perks and flexible PTO; potential reimbursements and lifestyle accounts
Back to all jobs