Staff Engineer - Model Behavior & Prompt Design

Doist; San Francisco (CA); On-site; USD 150,000 - 210,000; Full time

Job summary

Doist is seeking software engineers for the Model Behavior team to shape how Perplexity’s AI products respond, including prompts, tools, memory, and skill usage. You’ll influence model behavior across domains, with an analytical, experiment-driven approach.

You’ll design context and prompt engineering strategies, test them at scale, and collaborate with engineers to improve tool integration and memory usage across our products.

Qualifications

• 2 to 10+ years of experience in software engineering or research.
• Strong background in software engineering fundamentals, and a technical understanding of LLM-driven and agentic systems.
• Experience shaping LLM behavior through prompts, tool and skill design, or memory systems.
• Strong written and verbal communication skills, particularly in explaining complex concepts to diverse stakeholders.

Responsibilities

• Context Engineering: design, test, and optimize prompts, skills, tools, and memory to shape Perplexity responses across products.
• Model Releases: help experiment with and release new models.
• Research & Analysis: identify inconsistencies and failure modes in model outputs through well-designed research projects.
• Knowledge Sharing: help engineers across teams build intuition for prompt design and context engineering best practices.
• Staying Current: track the latest prompting and alignment techniques and bring ideas back to the team.

Skills

Software engineering

LLM / AI systems

Prompt design

Memory systems

Communication

Education

Bachelor's degree in Computer Science or related field

Tools

Python

LLM tooling

APIs

Job description

Doist is seeking software engineers for the Model Behavior team to shape how Perplexity’s AI products respond, including prompts, tools, memory, and skill usage. You’ll influence model behavior across domains, with an analytical, experiment-driven approach.

You’ll design context and prompt engineering strategies, test them at scale, and collaborate with engineers to improve tool integration and memory usage across our products.