Crogl
AI Engineer
United States · Remote · Full-time · Posted Jun 30, 2026
About the job
Build and improve production LLM-powered agents for security workflows, with a major focus on evaluating their quality, reliability, and business impact.
What you'll do
- Build agentic AI features and infrastructure for experimentation, deployment, monitoring, and production use.
- Design and maintain benchmarks, datasets, automated evaluations, regression tests, and observability systems for agents.
- Investigate agent failures and collaborate with customers and internal teams to improve AI performance in security workflows.
What they ask for
- Strong programming skills, preferably in Python.
- Solid software engineering fundamentals, including testing, debugging, and system design.
- Experience building applications, projects, or products using LLMs and modern AI tools.
- Ability to design experiments, interpret results, and make data-driven decisions.
Nice to have
- Experience building AI agents, copilots, or workflow automation systems, or designing AI evaluations and benchmarks.
- Familiarity with OpenAI, Anthropic, Gemini, open-source LLMs, retrieval systems, vector databases, RAG, LangGraph, OpenAI Agents SDK, MCP, AI observability, or cybersecurity.
Tools
Python, OpenAI, Anthropic, Gemini, LangGraph, OpenAI Agents SDK, MCP
AI focus
Build and evaluate production AI agents for security investigations and workflows, including prompt, tool-use, retrieval, memory, planning, and reasoning strategies.
Model-written summary · the original posting is authoritative