Perplexity

AI

MemberofTechnicalStaff(ModelBehaviorArchitect)

$180–270k San Francisco, California, United States FULL TIME
Market Sentiment
HIGH DEMAND

Neural analysis suggests this role is
optimal for Mid candidates.

The Brief

“Member of Technical Staff (Model Behavior Architect) at Perplexity. Skills: Model Behavior Architect, AI products and evaluations, prompt and context engineering strategies, model capabilities, AI infrastructure, prompting, model quality, behavioral consistency. Design, test, and optimize context strategies and system prompts that shape answer engine behavior across products, features, and use cases. Build automated and semi-automated evaluation pipelines that measure model quality, catch regres”

What You'll Achieve.

deliver high quality user experiences across multiple domains and models; create a stellar product experience for our users; ensuring smooth transitions with no degradation; improving AI system performance through systematic evaluation and iteration; making AI more reliable and useful for our users

Industry & Context.

AI
Problems you'll solve

Get excited about edge cases in model behavior and love digging into how an answer could be better; Enjoy turning qualitative "this feels off" intuitions into quantitative metrics and systematic fixes; Are comfortable with ambiguity and can define what "good" looks like for novel AI features

What They're Looking For.

Must Have

Experience designing evaluations, benchmarks, or metrics for AI systems, written and verbal communication skills, particularly in explaining complex concepts to diverse stakeholders, Ability to manage multiple concurrent projects in a fast-moving environment, experience with Perplexity or other frontier AI models in production settings, Demonstrated experience with Python — you'll prototype, debug, automate, and build systems at scale, 3+ years of experience working with LLMs in a product or research setting

Nice to Have

Experience with A testing or experimentation frameworks, Track record of improving AI system performance through systematic evaluation and iteration

What You'll Do.

and optimize context strategies and system prompts that shape answer engine behavior across products

Build automated and semi-automated evaluation pipelines that measure model quality

and scale across product surfaces

Partner with research and engineering to validate model behavior before and during rollouts

ensuring smooth transitions with no degradation

Identify inconsistencies and failure modes in model outputs through well-designed research projects — for both internal and production-facing systems

Help engineers across teams build intuition for prompt design

and evaluation best practices

Track the latest alignment

and prompting techniques from industry and academia

and bring the best ideas back to the team

How You'll Work.

Team & Collaboration

collaborate closely with research and product teams; Cross-functional Collaboration: Work closely with design, product, and research teams to translate product goals into concrete model behavior requirements; Knowledge Sharing: Help engineers across teams build intuition for prompt design, context engineering, and evaluation best practices

Communication Scope

written and verbal communication skills, particularly in explaining complex concepts to diverse stakeholders

Process & Methodology

Ability to manage multiple concurrent projects in a fast-moving environment

Full Job Description

ABOUT THE ROLE We're looking for a Model Behavior Architect to help build Perplexity's AI products and evaluations. You'll sit within our AI team and collaborate closely with research and product teams, designing prompt and context engineering strategies to deliver high quality user experiences across multiple domains and models. This role is equal parts craft and science. You'll develop a deep understanding of our answer engine by pressure-testing model capabilities and working across our AI infrastructure (including system and tool prompts, skills, and evaluations) to create a stellar product experience for our users. You'll serve as a go-to expert on prompting, model quality, and behavioral consistency across new product features and model releases. KEY RESPONSIBILITIES - Context Engineering: Design, test, and optimize context strategies and system prompts that shape answer engine behavior across products, features, and use cases. - Evaluation Systems: Build automated and semi-automated evaluation pipelines that measure model quality, catch regressions, and scale across product surfaces. - Model Launch Support: Partner with research and engineering to validate model behavior before and during rollouts, ensuring smooth transitions with no degradation. - Research & Analysis: Identify inconsistencies and failure modes in model outputs through well-designed research projects — for both internal and production-facing systems. - Cross-functional Collaboration: Work closely with design, product, and research teams to translate product goals into concrete model behavior requirements. - Knowledge Sharing: Help engineers across teams build intuition for prompt design, context engineering, and evaluation best practices. - Staying Current: Track the latest alignment, evaluation, and prompting techniques from industry and academia, and bring the best ideas back to the team. WHAT WE'RE LOOKING FOR REQUIRED - Experience designing evaluations, benchmarks, or metrics for AI syste

Free ATS check

Applying for this Member of Technical Staff (Model Behavior Architect) role?

Most applicants get filtered before a human reads their resume. See if yours makes the cut.

How to Apply on Ashby

  • Ashby is a fast modern ATS — most applications take under 3 minutes.
  • The resume parser is strong; verify parsed experience dates and job titles.
  • Custom screening questions are often scored algorithmically — answer completely.
  • Location field affects geo-based screening; use your actual metro area.

ANONYMOUS · UNFILTERED

What do employees actually say about Perplexity?

Real rants from real employees. Read before you apply.

Read Company Rants →