Staff Software Engineer, AI Platform & Infrastructure
Core
Build backend and AWS platform infrastructure for autonomous AI agents (Digital Workers) that perform identity operations and security tasks for enterprise customers.
Role type
Staff Software Engineer (AI Platform & Infrastructure)
Builds
Autonomous agent execution services, workflow connectors, data infrastructure, and production reliability systems for Okta's Digital Workers product.
Domain
AI Infrastructure / Cloud Platform / Identity Security
Deliverable
production ML models
Required skills
Python, AWS (Step Functions, SQS, EventBridge, Lambda, API Gateway, IAM, RDS), PostgreSQL, SQL, Infrastructure as Code, Observability, Distributed Systems, Tenant Isolation, Async System Design
Preferred skills
ClickHouse, BigQuery, Multi-tenant SaaS, OAuth/OIDC/SAML/SCIM, Agent Frameworks (LangGraph, Claude Agent SDK, Codex SDK)
Technologies
Python, FastAPI, AWS Step Functions, SQS, EventBridge, API Gateway, Lambda, RDS PostgreSQL, pgvector, S3, KMS, Secrets Manager, CloudWatch, CloudTrail, ClickHouse, BigQuery, React, AWS Amplify, OpenAI, Anthropic
Responsibilities
Design and build Python FastAPI services and reusable connectors for enterprise applications; Implement durable execution workflows handling approvals, rate limits, and retries; Manage PostgreSQL schemas, indexes, and pgvector retrieval for tenant isolation; Build model API access controls for OpenAI and Anthropic; Create analytics pipelines for worker events and usage reconciliation; Build deployment pipelines, IaC, and observability controls; Implement scoped write services, kill switches, and audit retention mechanisms.
Seniority
Staff, domain leadership across teams
