Prepin
Log in
TasteTech

engineering opportunity

AI Engineer (Full-stack)

You will build agentic workflows and product surfaces that integrate AI models into user-facing applications. This role involves working across the full stack to turn raw model outputs into polished, usable design tools.

San Francisco, California, United StatesonsiteFULL_TIME

Posted

About the role

What will you do at TasteTech?

Taste is building the AI for creative work. Today’s AI is great at logic and code, but when it comes to anything visual, brand, or aesthetic, it produces slop. Generic fonts, cluttered layouts, off-brand colors, soulless compositions.

The models don’t understand taste. We’re changing that. We’re building the creativity layer for AI: the models, evaluators, and data pipelines that teach AI what “great” actually looks like, so that every company building with AI can ship work that feels crafted, on-brand, and beautiful.

We recently closed a $16M seed round co-led by Amplify and CRV. We’re working with customers like Anthropic, Flint, and leading AI labs, powering the design intelligence behind their products. The team today is small, senior, and hungry.

We care deeply about quality, move fast, and love the problem. If you think AI-generated work feels soulless right now, and you want to be part of the team fixing that, we’d love to meet you. We’re hiring an AI Engineer with a full-stack spike to build the product layer around our models — the agent flows, the creative tooling, the consumer-facing product sense that makes our tech actually usable.

You’ll own end-to-end features: from “how does the agent think through this design task” all the way to “how does the user experience it in the UI.” You’ll work closely with Thais, our founding designer, and our ML team.

WHAT YOU’LL WORK ON Building agentic workflows that orchestrate models, tools, and human feedback Shipping product surfaces — brand extractors, prompt enhancers, design QA tooling Integrating our models into customer products (API + embedded experiences) Making taste tangible: turning raw model outputs into something designers actually love to use Working across the stack — TypeScript/Next.js on the front, Python/FastAPI on the back, whatever the feature needs YOU MIGHT BE A FIT IF 3+ years building product-facing software, with recent AI/LLM work You’ve built with LangChain, LlamaIndex, or your own agent harness — and have opinions about all of them You care about the product, not just the infra You have strong aesthetic taste and sweat the last 10% of UX polish You love working with designers NOT A FIT IF You want to own only backend infra without touching product You don’t enjoy the messiness of prototyping AI UX patterns Most of your recent work is at companies with >500 engineers

Which skills does this role require?

TypeScriptNext.jsPythonFastAPILangChainLlamaIndexAI EngineeringLLMFull-stack DevelopmentAgentic WorkflowsProduct DesignUX PolishAPI IntegrationCreative ToolingAI EngineerFull-stackUXUIAPIDesign QAProduct EngineeringPrototypingJavaScriptMachine LearningLLMs

Make your next move

Build a shortlist and prepare

Identify the requirements you can demonstrate, then choose examples from your work to discuss with the hiring team.

Review the responsibilities and requirements before adding an opening to your shortlist.

Role information can change. Confirm current details on the original application page.

Product

AI Candidate AgentCompaniesBrowse JobsDeep ProfileSkill AssessmentOpportunity Matching
Prepin.ai

© 2026 Prepin | All rights reserved.