Member of Technical Staff Model Behavior

You will design, test, and optimize prompts, tools, skills, and memory that shape AI responses. You will build self-improvement loops, experiment with model releases, investigate model failures, share context-engineering practices, and track emerging prompting and alignment techniques.

Responsibilities

• Design, test, and optimize prompts, skills, tools, and memory
• Build self-improvement loops for prompts, tool use, skill use, and memory
• Experiment with and release new models
• Identify inconsistencies and failure modes in model outputs
• Share prompt-design and context-engineering practices
• Track prompting, context-engineering, and alignment techniques

Requirements

• 2 to 10+ years of software engineering or research experience
• Software engineering fundamentals
• Technical understanding of LLM-driven and agentic systems
• Experience shaping LLM behavior through prompts, tool and skill design, or memory systems
• Written and verbal communication

Benefits

• Equity
• Health insurance
• Dental insurance
• Vision insurance
• Retirement benefits
• Fitness account
• Commuter account
• Dependent care account