The opportunity
Secure Every Identity, from AI to Human Identity is the key to unlocking the potential of AI. Okta secures AI by building the trusted, neutral infrastructure that enables organizations to safely embrace this new era.
What you'll do
Build the agent harness for planning, tool use, memory, context compaction,: interruption and recovery during long-running work.
Integrate OpenAI and Anthropic model APIs. Select models using measured: quality, latency and cost, with clear failure handling.
Evaluate existing harnesses and build only the missing pieces. Keep the: harness connected to AWS workflow execution and approval state.
Keep authorization and sensitive writes behind application policy checks.: Require evidence of the 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.
What they're looking for
- 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.
- 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 includes Claude Agent SDK, OpenAI Codex SDK, Strands Agents, LangChain Deep Agents, LangGraph or a custom implementation.
