Model Behavior Architect

3 Months ago • All levels

Job Summary

Job Description

The Model Behavior Architect will be responsible for shaping systems that reliably answer user questions. This involves designing, refining, and implementing prompt engineering strategies across research and general knowledge use cases. The role requires identifying edge cases and inconsistencies in model outputs through structured testing and prompt iteration. The architect will develop automated and semi-automated pipelines for evaluating prompt effectiveness at scale, collaborating with researchers, PMs, and engineers to align model behavior with product goals. They will also collect and synthesize feedback to improve prompt design and contribute to prompt libraries for internal and production systems. Staying up-to-date with the latest techniques in prompt engineering is essential.

Must have:

Demonstrated passion for AI and prompt engineering projects.
Background in relevant fields like philosophy or data science.
Familiarity with Python and running scripts.
Understanding of LLMs, training, and RL.
Excellent communication skills for teaching complex concepts.
Creative problem-solving abilities.

Perks:

Comprehensive health, dental, and vision insurance.
401(k) plan.
Equity may be part of the total compensation package.

3 skills required

3 skills required for this role

Add these skills to join the top 1% applicants for this job

communication

data-science

python

Job Details

Perplexity is looking for a Model Behavior Architect to help shape systems that reliably answer users' questions.

Responsibilities

Design, refine, and implement prompt engineering strategies to guide model behavior across research and general knowledge use cases
Identify edge cases and behavioral inconsistencies in model outputs through structured testing and prompt iteration
Develop automated and semi-automated pipelines for evaluating prompt effectiveness at scale
Work cross-functionally with researchers, PMs, and engineers to align model behavior with product goals
Collect and synthesize qualitative and quantitative feedback to inform prompt design improvements
Collaborate on prompt libraries and reusable frameworks for internal and production-facing systems
Stay current with the latest prompt engineering, alignment, and evaluation techniques from both industry and academia

Qualifications

Demonstrated passion for AI and can share specific prompt engineering and chaining projects you're proud of
Background in philosophy, psychology, linguistics, data science, or related fields
Familiar with Python and running simple scripts
High-level understanding of LLMs, training, RL
Excellent communication skills, particularly in teaching complex concepts
Creative problem-solving abilities with a "hacker spirit" for solving puzzles

At Perplexity, we've experienced tremendous growth and adoption since publicly launching the world's first fully functional conversational answer engine in 2022. We've grown from answering 2.5 million questions per day at the start of 2024 to around 20 million daily queries in December 2024. We also offer Perplexity Enterprise Pro, which counts leading companies like Nvidia, the Cleveland Cavaliers, Bridgewater, and Zoom as customers.

To support our rapid expansion, we've raised significant funding from some of the most respected technology investors. Our investor base includes IVP, NEA, Jeff Bezos, NVIDIA, Databricks, Bessemer Venture Partners, Elad Gil, Nat Friedman, Daniel Gross, Naval Ravikant, Tobi Lutke, and many other visionary individuals. In 2024, our employee base grew nearly 300%, and we're just getting started.

Final offer amounts are determined by multiple factors, including, experience and expertise, and may vary from the amounts listed above.

Equity: In addition to the base salary, equity may be part of the total compensation package.
Benefits: Comprehensive health, dental, and vision insurance for you and your dependents. Includes a 401(k) plan.