> Markdown version of [/jobs/ext/4260472-software-architect-ai-systems-and-platform](https://www.wearedevelopers.com/jobs/ext/4260472-software-architect-ai-systems-and-platform). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Software Architect, AI Systems and Platform

- **Company:** Okta, Inc.
- **Location:** San Francisco, CA, United States
- **Salary:** $274,000.0
- **Contract:** Permanent contract
- **Skills:** LangGraph Framework, Application Programming Interfaces (APIs), Artificial Intelligence, Amazon Web Services, Amazon S3, BigQuery, Cloud Computing Security, PostgreSQL, OAuth, Open Source Technology, OpenID, Software Architecture, OpenAI, Security Assertion Markup Language (SAML), Systems Architecture, Systems Integration, TypeScript, Model-Driven Development, ReactJS, AgentCore, Backend, Fastapi, Servicebus, Pgvector, Amazon Bedrock, Production Code, Vertica, Claude, Functional Programming, Api Design, Cloudwatch, Api Gateway, OpenAI Codex, Amazon Simple Queue Service (SQS), Agent SDK, Api Management
- **Published:** October 23, 2026
- **Apply:** https://www.careerbuilder.com/job-details/software-architect-ai-systems-and-platform-san-francisco-ca--f28b6ea8-c127-4039-ac31-a6ee1d97ca6f

## About the Role

Software Architecture, Artificial Intelligence (AI), System Architecture, Artificial Intelligence (AI), Software Architecture, Startup, Operations Security (OPSEC), Failure Analysis, Application Programming Interface (API), Quality Metrics, Hands-on builder: You still write production code and test important decisions through implementation.

Practical architect: You choose a small, clear design and make it easy to extend when the product grows.

Trusted partner: You earn confidence through useful code, clear feedback and customer understanding., * A 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.
 * The ability to explain design tradeoffs, guide senior engineers and remain accountable through implementation.
 * Depth in at least one of the two role areas below, plus the ability to work across the full product.

## Description

* Define and implement shared contracts for tasks, events, permissions, approvals, evidence and usage.
 * Set clear boundaries between model reasoning, agent harnesses, durable workflows and services that enforce authorization.
 * Select a harness through representative identity tasks, failure tests and operational evidence. Keep model providers and harness components replaceable.
 * Design integrations with OpenAI and Anthropic APIs, including data boundaries, latency, cost, version changes and measured release quality.
 * Build reference services for tenant isolation, scoped tool execution, idempotency, long approval waits and verified results.
 * Define the transactional and analytics data architecture. Keep PostgreSQL application state separate from the planned ClickHouse or BigQuery analytics layer.
 * Connect Product, Applied AI and Platform engineers through clear ownership and practical APIs. Resolve dependencies that slow delivery.
 * Write critical implementations, review recovery and security, and guide technical leads through production rollout and customer expansion., AI systems architect: Build and evaluate agent harnesses, context management, model integrations and quality controls. Relevant experience includes Claude Agent SDK, OpenAI Codex SDK, Strands Agents, LangChain Deep Agents, LangGraph or a comparable custom runtime.

Platform architect: Lead backend, connector, security, data and workflow architecture. Bring deep production systems experience and practical knowledge of integrating model-driven workflows.

Our stack

Python FastAPI, React and TypeScript, AWS Amplify, Step Functions, Amazon Bedrock AgentCore, Lambda, SQS, EventBridge and API Gateway. Storage uses RDS PostgreSQL, pgvector and S3. Security and operations include KMS, Secrets Manager, CloudWatch and CloudTrail.

We are adding OpenAI and Anthropic model API integrations. An agent harness and a dedicated analytics layer using ClickHouse or BigQuery are planned. You will help choose and implement them.

And extra credit for

 * Enterprise identity, security products, OAuth, OIDC, SAML, SCIM or complex customer integrations.
 * ClickHouse, BigQuery, agent evaluations, post-training systems or open-source infrastructure.
 * Building a new product within a larger enterprise and keeping technical decisions reversible.