SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 165,000 - 226,600 / annual
Okta is building Digital Workers, a suite of autonomous agents for identity operations and security. This role is on the team that built Jeeva AI, working directly with Okta's co-founder and CEO Todd McKinnon. You will have the ownership and pace of a startup combined with the resources of a public company, bringing this product to Okta's 20,000+ customers.
You will own the backend and AWS platform infrastructure that keeps autonomous workers running reliably. The team owns services, connectors, workflow execution, data pipelines, and production reliability. You will write Python services and infrastructure code that enable workers to make approved changes while preserving audit evidence.
Key responsibilities include:
- Build Python FastAPI services, data models, and reusable connectors for Okta, AWS, ServiceNow, and enterprise applications
- Implement durable execution patterns using Step Functions, SQS, and EventBridge, handling approval waits, rate limits, duplicate events, and safe retries
- Manage PostgreSQL schemas, indexes, query performance, and pgvector retrieval with strict tenant isolation across APIs, storage, and credentials
- Build model API access for OpenAI, Anthropic, and AWS paths with credential management, quotas, timeouts, and cost controls
- Design analytics pipelines for worker events, traces, tokens, findings, and verified outcomes (evaluating ClickHouse and BigQuery)
- Create reliable usage records and reconciliation to prevent duplicate counting and incomplete work from being marked as new outcomes
- Build deployment pipelines, infrastructure as code, observability, and safe release controls across dev, staging, and production
- Implement scoped write services, kill switches, audit retention, and backup recovery with comprehensive failure testing
The role operates at the Senior level, owning a backend or platform component including deployment, tests, and production operation. You will be a reliable builder who designs for failure and proves recovery works, a hands-on engineer who writes production services and improves developer tools, and a strong owner who follows changes through deployment, monitoring, and production support.
Tech stack: Python FastAPI, AWS (Step Functions, Bedrock AgentCore, Lambda, SQS, EventBridge, API Gateway, containers), RDS PostgreSQL, pgvector, S3 Object Lock, KMS, Secrets Manager, CloudWatch, CloudTrail, React, and AWS Amplify. The team is also integrating OpenAI and Anthropic models, building an agent harness, and adding dedicated analytics infrastructure.
REQUIREMENTS:
- Experience building and operating production backend or distributed systems with strong coding skills in Python or comparable language
- Hands-on AWS experience with APIs, queues, containers, networking, IAM, and databases
- Strong SQL and data modeling skills with experience diagnosing database performance and asynchronous system failures
- Experience with infrastructure as code, deployment automation, observability, and production incident response
- Sound judgment about customer data, tenant isolation, credentials, and safe changes to external systems
Extra credit for:
- ClickHouse, BigQuery, or comparable analytics systems, event ingestion, and usage metering
- Multi-tenant SaaS, OAuth, OIDC, SAML, SCIM, or enterprise connector development
- Deploying agent frameworks including Claude Agent SDK, Codex SDK, Strands Agents, Deep Agents, or LangGraph
