SlipstreamJobsFresh Startup & VC-Backed Jobs

Software Architect, AI Systems and Platform

Okta - San Francisco, CA, USA - In-office - posted 2026-10-23

Apply on the company site

SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.

Salary: USD 274,000 - 376,200 / annual

Okta is hiring two hands-on Software Architects to lead the design and implementation of Digital Workers, a new suite of autonomous agents for identity operations and security. You will work directly with Todd McKinnon, Okta's co-founder and CEO, bringing a startup's ownership and pace to a public company with 20,000+ customers. One architect will lead agent execution, harnesses, and evaluations. The other will lead backend services, integrations, data, and platform reliability. Both roles require writing critical production code, resolving cross-team architectural decisions, and guiding technical leads through production rollout and customer expansion. Key responsibilities include: - Define and implement shared contracts for tasks, events, permissions, approvals, evidence, and usage across the platform - Set clear boundaries between model reasoning, agent harnesses, durable workflows, and authorization services - Select and evaluate agent harnesses through representative identity tasks, failure tests, and operational evidence while keeping components replaceable - Design integrations with OpenAI and Anthropic APIs, managing data boundaries, latency, cost, versioning, and release quality - Build reference services for tenant isolation, scoped tool execution, idempotency, long approval waits, and verified results - Define transactional and analytics data architecture, separating PostgreSQL application state from planned ClickHouse or BigQuery analytics - Connect Product, Applied AI, and Platform engineers through clear ownership and practical APIs - Write critical implementations, review recovery and security, and guide teams through production rollout The tech stack includes Python FastAPI, React, TypeScript, AWS (Amplify, Step Functions, Bedrock AgentCore, Lambda, SQS, EventBridge, API Gateway), RDS PostgreSQL with pgvector, S3, KMS, Secrets Manager, CloudWatch, and CloudTrail. You will help evaluate and implement OpenAI/Anthropic integrations, agent harnesses, and analytics layers. Requirements: - Record of leading architecture and delivery across multiple engineering teams with recent production code you personally implemented - Deep knowledge of distributed services, API design, data consistency, cloud security, and production operations - Experience making systems simpler while improving reliability, security, or delivery speed - Ability to explain design tradeoffs, guide senior engineers, and remain accountable through implementation - Depth in at least one of the two role areas (AI systems or platform architecture) plus ability to work across the full product For AI Systems Architect focus: Experience with Claude Agent SDK, OpenAI Codex SDK, Strands Agents, LangChain Deep Agents, LangGraph, or comparable custom runtimes. For Platform Architect focus: Deep production systems experience and practical knowledge of integrating model-driven workflows. Extra credit for: Enterprise identity and security products (OAuth, OIDC, SAML, SCIM), complex customer integrations, ClickHouse, BigQuery, agent evaluations, post-training systems, open-source infrastructure, or experience building new products within larger enterprises while keeping technical decisions reversible.

Similar roles