Autonomous Offensive AI Engineer for Pentest Agents

Parameter; San Francisco (CA); Hybrid; USD 180,000 - 240,000; Full time

Job summary

Parameter builds AI agents that perform autonomous penetration tests against production applications and cloud environments, identifying IDORs, broken access control, XSS, and misconfigurations that scanners miss. You’ll design the agent systems, reasoning loops, tool interfaces, and memory architecture to enable an LLM to behave like a skilled offensive security researcher rather than a simple tester.

This role is onsite in San Francisco, offering a fast-moving, hands-on environment with

Qualifications

• 3+ years in software engineering with production LLM experience.
• Strong TypeScript, async/distributed systems, and long-running workflows.
• Ability to design context engineering and robust agent tooling.
• Experience with eval harnesses and understanding offline vs production metrics.

Responsibilities

• Design and ship agent workflows in LangGraph and Temporal that plan, execute, and verify multi-step exploitation chains.
• Build the tool layer the agents operate through: HTTP clients, auth handling, browser control, cloud enumeration, payload generation.
• Own the eval loop. Define what 'good' means for agent runs and optimize metrics.
• Reduce false positives to improve customer trust and value.
• Manage inference cost and latency, including prompt caching and model selection across providers.

Skills

TypeScript

LLM systems

Context engineering

Eval harness

Distributed systems

Async workflows

Tools

LangGraph

Temporal

GCP

AWS Bedrock

Anthropic API

Langfuse

Braintrust

GitHub Actions

Linear

Graphite

Job description

Parameter builds AI agents that perform autonomous penetration tests against production applications and cloud environments, identifying IDORs, broken access control, XSS, and misconfigurations that scanners miss. You’ll design the agent systems, reasoning loops, tool interfaces, and memory architecture to enable an LLM to behave like a skilled offensive security researcher rather than a simple tester.

This role is onsite in San Francisco, offering a fast-moving, hands-on environment with