AI/ML Engineer — LLM Security Applications

Role overview Design and improve a multi-agent AI pipeline that helps detect software vulnerabilities. The role focuses on prompt and agent-system design across several hosted and custom language models, with attention to measuring the accuracy of AI outputs.

Responsibilities - Develop and refine multi-agent workflows for vulnerability detection. - Work with Groq, Claude, Gemini, and custom fine-tuned models. - Apply evaluation methods to assess AI accuracy and guide improvements.

Requirements - Strong background in LLM prompt engineering and agentic systems. - Experience with LangChain, LangGraph, or a comparable framework. - Familiarity with evaluation frameworks for AI accuracy.

Nice to have - Knowledge of security and vulnerability analysis.

Benefits and work setup - Full-time, remote role open to candidates worldwide.