LLM Engineer | Remote

Role Responsibilities

• Utilize autonomous AI coding agents to execute and document complex software engineering workflows.
• Plan, implement, debug, and refactor code with AI agents, providing detailed feedback on outcomes.
• Evaluate AI-generated code, identifying errors and opportunities for improvement.
• Compare outputs across AI systems and document findings on reasoning quality and performance.
• Draft best practices and process documentation for AI agent workflows, emphasizing clarity and reproducibility.
• Deliver feedback on agentic development environments, including coding assistants and automation tools.

Requirements

• Demonstrated proficiency in delegating multi-step technical tasks to AI systems and refining results.
• Strong understanding of prompt engineering and evaluation of AI-generated outputs.
• Background in software engineering, DevOps, data science, ML engineering, or technical automation.
• Familiarity with agentic development environments and leading AI coding assistants.
• Exceptional written and verbal English communication skills for documenting workflows and feedback.
• Experience with multiple AI-powered development tools and systems.