Product Designer

Meta Business Agent aims to provide every business with a multi-modal AI agent that can answer customer questions, help close sales, book appointments, and provide customer support 24/7. We're looking for a product designer to help us bring this vision to life, end to end. You'll have the opportunity to play a central role in the way we build this technology, from prototyping new experiences to designing the system prompts and evals that ensure every agent meets the quality bar of Meta and the businesses who use them.

In this role, you'll utilize your full range of product design, interaction design, and model design skills, while contributing to high-level strategic decisions with product and executive partners. This role spans both business-facing and customer-facing agent experiences across chat, voice and visual surfaces, for businesses ranging from small businesses to enterprises.

Responsibilities

Write and revise the prompts behind Meta's agentic tools, features, and behaviors on a product surface; test the surface, turn findings into prompt fixes, ship them, and confirm that the prompt users get is the one intended Package what prompting can't fix for training, with the eval attached: graders for crisp behaviors, and human-feedback questions and good/bad pairs for fuzzy ones like writing quality Partner closely with engineering and data science to define what good looks like in agent output across chat, voice and visual surfaces, and drive the eval strategy that measures it Extend eval coverage beyond text to voice and visual agent output, defining how quality is judged when the surface itself is conversational or visual Define quality bars that hold across a long tail of businesses, so a single agent specification works from small business through enterprise without bespoke rework Rapidly prototype new ideas and experiences to bring concepts to life and help the team prioritize new workstreams based on impact and feasibility Define, evolve, and unify visual and interaction systems that scale across products and platforms Define eval strategy, build evals, golden sets, judges, etc alone and in collaboration with data science and engineering Use your familiarity with how code works in software, updating language and prompts in code with internal tools, reviewing changes to confirm the shipped experience is as intended, and building the logic that adapts an agent's behavior to context Work with product and cross-functional partners to define a strategy for multi-modal agent communication Represent the design strategy and rationale to leadership and cross-functional executives, shaping organizational alignment on product direction and influencing org-wide priorities across product, engineering, research, and content strategy

Qualifications

Bachelor's Degree in HCI, design, other related fields or work experience in designing and building agentic experiences 11+ years designing software products with a focus on user experience, interaction and visual design that meet business objectives Experience building and maintaining evaluation pipelines for LLM products: graders, rubrics, comparison sets, regression suites, and the plumbing that runs them across models Experience designing and building agentic experiences B2C or B2B experience Deep expertise in prototyping tools and the ability to evaluate and advance design craft across fidelity levels Experience adhering to and implementing responsible, ethical AI practices (e.g., risk assessment, bias mitigation, quality and accuracy reviews) Demonstrated ability to integrate AI tools to optimize/redesign workflows and drive measurable impact (e.g., efficiency gains, quality improvements) Demonstrated ability to integrate AI tools to optimize or redesign workflows and drive measurable impact, for example, efficiency gains or quality improvements Has turned product rubrics into training signal: graders, human-feedback questions, or preference pairs Experience adhering to and implementing responsible, ethical AI practices, for example risk assessment, bias mitigation, quality and accuracy reviews Experience shaping agent behavior on voice or other multi-modal surfaces Demonstrated ongoing AI skill development (e.g., prompt/context engineering, agent orchestration) and staying current with emerging AI technologies Demonstrated ongoing AI skill development, for example prompt and context engineering or agent orchestration, and staying current with emerging AI technologies AI-native design fluency, meaning experience with model design, generative AI logic, and defining assistant behavior and tone at the systems layer, not just surface-level copy Front-end or notebook-to-app experience, and opinions about what makes an eval result legible at a glance Experience with both B2C and B2B experience preferred