Staff Software Engineer, Applied AI
San Francisco · USD 194,000-267,000 / year · Posted Oct 15, 2026
At a glance
- Location
- San Francisco
- Salary
- USD 194,000-267,000 / year · Base salary
About the role
- The Staff Software Engineer will join a team building Digital Workers, a suite of autonomous agents for identity operations and security.
- This role involves working directly with Okta's CEO to develop reliable agent harnesses and evaluation systems for enterprise-scale AI applications.
- The position offers the ownership and pace of a startup environment supported by the resources of a public company.
Responsibilities
- Build agent harnesses for planning, tool use, memory, context compaction, interruption, and recovery.
- Integrate OpenAI and Anthropic model APIs while managing quality, latency, and cost.
- Maintain harness connectivity to AWS workflow execution and approval state.
- Implement application policy checks for authorization and sensitive writes.
- Build evaluation datasets and replay tests for findings, access decisions, and agent onboarding.
- Measure metrics including false positives, missed risks, unsafe actions, and completion rates.
- Turn production failures into regression tests.
- Test for prompt injection, stale evidence, conflicting instructions, and unsafe tool use.
- Improve prompts, retrieval, tools, and model routing.
- Evaluate fine-tuning or post-training methods when results justify them.
Requirements
- Strong Python engineering skills.
- Experience shipping an LLM application that uses tools.
- Hands-on experience building agent workflows or evaluation systems for tool-using LLM applications.
- Experience integrating model APIs, structured outputs, and asynchronous services.
- Depth in agent execution or evaluation systems with explainable failure analysis.
- Ability to distinguish plausible model responses from supported findings or verified actions.
Preferred qualifications
- Open-source contributions
- Agent observability
- Security evaluations
- Synthetic evaluation data
- Fine-tuning
- Preference data
- Post-training evaluation
- Model distillation
Benefits
- Health insurance
- Dental insurance
- Vision insurance
- 401(k)
- Flexible spending account
- Paid leave (PTO)
- Parental leave
- Equity
- Bonus
Workplace
- Role is based in San Francisco.
Skills
- Python
- FastAPI
- AWS Step Functions
- Amazon Bedrock
- PostgreSQL
- Pgvector
- Claude Agent SDK
- OpenAI Codex SDK
- LangChain
- LangGraph
- ClickHouse
- BigQuery