Member of Technical Staff (Model Behavior)
Remote • San Francisco • FullTime
Posted 1mo ago
Remote Work Policy
Fully remote
Employment Type
FullTime
Categories
Applied AI Engineer
About the job
We are seeking software engineers for our Model Behavior team to influence the behavior of Perplexity's AI products, focusing on response style, and the utilization of tools, skills, and memory. This role involves designing prompt and context engineering strategies to ensure high-quality user experiences across various domains and models. The ideal candidate possesses a robust software engineering background and an analytical, experiment-driven mindset for tackling complex challenges. You will be instrumental in refining context and prompt engineering to shape model behavior, style, and the effective use of tools, skills, and memory within our products.
Responsibilities
- Design, test, and optimize prompts, skills, tools, and memory to shape AI responses across products, features, and use cases.
- Build self-improvement loops to guide prompts, enhance tool/skill utilization, and improve memory recall.
- Assist in experimenting with and releasing new models.
- Conduct research and analysis to identify inconsistencies and failure modes in model outputs for internal and production systems.
- Facilitate knowledge sharing among engineers regarding prompt design and context engineering best practices.
- Stay updated on the latest prompting, context engineering, and alignment techniques from industry and academia, and integrate them into the team's work.
Requirements
- 2 to 10+ years of experience in software engineering or research.
- Strong foundation in software engineering fundamentals.
- Technical understanding of LLM-driven and agentic systems.
- Experience shaping LLM behavior via prompts, tool/skill design, or memory systems.
- Excellent written and verbal communication skills, with the ability to explain complex concepts to diverse audiences.
- Recent experience working on modern LLM-driven products (nice to have).
- Experience collaborating across teams or with external partners (nice to have).
- Experience designing evaluations or benchmarks for AI systems (nice to have).