Drimva

Parameter

Member of Technical Staff, AI Engineer

$180K–$240K

San Francisco, CA, US · Staff · Full-time · Posted Oct 5, 2026

Experience
3+ years of software engineering, with at least one year building production LLM systems.
Visa sponsorship
Must be authorized to work in the US; visa sponsorship is not available.

About the job

Build and ship autonomous AI agents that perform penetration testing against production applications and cloud environments.

What you'll do

  • Design agent workflows that plan, execute, and verify multi-step exploitation chains; build the tools agents use.
  • Own agent evaluations and reduce false positives.
  • Manage inference cost and latency, including prompt caching, context strategy, and model selection.

What they ask for

  • 3+ years of software engineering, including at least one year building production LLM systems.
  • Strong TypeScript skills and comfort with async systems, distributed systems, and long-running workflow orchestration.
  • Practical understanding of context engineering, tool design, and agent failure modes.
  • Experience building or maintaining an evaluation harness and understanding the gap between offline metrics and production behavior.

Nice to have

  • Security background, CTF experience, bug bounty history, or a track record of breaking things you were not supposed to break.

Pay

$180K – $240K (base salary; currency not stated)

Tools

TypeScript, LangGraph, Temporal, GCP, AWS Bedrock, Anthropic API, Langfuse, Braintrust

AI focus

Develop autonomous offensive-security agents and their reasoning loops, tools, memory, evaluations, and inference optimization.

Model-written summary · the original posting is authoritative

First seen Oct 29, 2026 · Last verified Nov 5, 2026 (UTC)