Staff Software Engineer, Applied AI

Okta•San Francisco, CA

8d•$194,000 - $267,000

About The Position

Okta is hiring a Staff Software Engineer for the team that built Jeeva AI and is developing Digital Workers, a suite of autonomous agents for identity operations and security. The team works directly with Okta’s co-founder and CEO and aims to bring the product to Okta’s 20,000+ customers. The role offers startup-style ownership and pace with the resources of a public company. You will build the harnesses and evaluation systems that help autonomous agents reliably investigate risk, use tools, wait for approvals, and complete tasks across enterprise systems. At the Staff level, you will lead a domain such as harnesses, evaluations, or model quality across workers and implement its critical components. The work includes integrating model APIs, connecting harness execution to AWS workflow and approval state, protecting authorization and sensitive actions with policy checks, verifying task outcomes, building evaluation datasets and replay tests, and turning production failures into regression tests. The core stack is Python FastAPI, AWS Step Functions, Amazon Bedrock AgentCore, PostgreSQL on Amazon RDS, and pgvector. OpenAI and Anthropic model APIs are part of the integration plan. The team plans to add an agent harness and a dedicated analytics layer using ClickHouse or BigQuery; the harness choice is open, and equivalent tools are relevant. The position’s annual base salary range for candidates in the San Francisco Bay Area is $194,000–$267,000 USD. Okta also offers equity where applicable, bonus, and benefits under applicable plans and policies. The role includes an immersive, in-person onboarding experience.

Requirements

Strong Python engineering skills and experience shipping an LLM application that uses tools.
Hands-on experience building agent workflows or evaluation systems for tool-using LLM applications.
For harness work, relevant experience may include Claude Agent SDK, OpenAI Codex SDK, Strands Agents, LangChain Deep Agents, LangGraph, or a custom implementation.
Experience integrating model APIs, structured outputs, and asynchronous services; experience with OpenAI or Anthropic is especially relevant.
Depth in agent execution or evaluation systems, with working code and failure analysis that can be explained.
Ability to distinguish a plausible model response from a supported finding or verified action.

Nice To Haves

Open-source contributions, agent observability, security evaluations, or synthetic evaluation data.
Fine-tuning, preference data, post-training evaluation, or model distillation using approved datasets.
Experience with identity and security workflows.
Foundation-model research experience is optional.
Experience with tools equivalent to the planned harness or analytics-layer tools.

Responsibilities

Build the agent harness for planning, tool use, memory, context compaction, interruption, and recovery during long-running work.
Integrate OpenAI and Anthropic model APIs and select models based on measured quality, latency, and cost, with clear failure handling.
Evaluate existing harnesses and build missing capabilities; connect the harness to AWS workflow execution and approval state.
Keep authorization and sensitive writes behind application policy checks, and require evidence of resulting state before marking work complete.
Build evaluation datasets and replay tests for valid findings, access decisions, app setup, and AI agent onboarding.
Measure false positives, missed risks, unsafe actions, completion rate, and cost; turn production failures into regression tests.
Test prompt injection, stale evidence, conflicting instructions, and unsafe tool use; protect tenant boundaries in retrieval and memory.
Improve prompts, retrieval, tools, and model routing; evaluate fine-tuning or other post-training methods when results justify them and data use is approved.
At the Staff level, lead a domain such as harnesses, evaluations, or model quality across workers and implement its critical components.