AI-First Staff Engineer — End-to-End Full-Stack ML

Sauce; Miami (FL); Remote; USD 90,000 - 150,000; Full time

Benefits offered by this job

Equity

Health insurance

Parental leave

Flexible work environment

Paid time off

Job summary

Sauce is seeking an experienced AI-first engineer to own the development of end-to-end AI-native features and deliver practical solutions to restaurant operators and customers. You’ll own frontend, backend, data, and model integration, shipping real products quickly on a small, fast-moving NYC team.

You’ll design and build end-to-end AI-powered capabilities, work with LLM APIs, and drive rapid iteration while collaborating with product and operations to solve real restaurant problems.

Qualifications

• Hands-on experience building with LLM APIs and SDKs.
• Strong full-stack ability from database to UI (TypeScript / Python).
• 8+ years of professional software engineering with 3+ years shipping production full-stack apps.
• Public trail: open-source repos, side projects, or demos with real users.

Responsibilities

• Take ambiguous product ideas from zero to shipped - design, build, deploy, and iterate, largely on your own.
• Build AI-native features (agents, RAG, tool-use, structured outputs, evals) as core product, not demos.
• Own the full stack: frontend, backend, data, model integration, glue in between.
• Stand up feedback loops - evals, telemetry, fast iteration for reliable AI products.

Skills

LLM APIs

Full-stack (TS/Python)

8+ years experience

Open-source / public trail

AI-first mindset

Product-minded

Fast iteration

Ambiguity tolerance

Tools

OpenAI API

Anthropic API

Open models

Job description

Sauce is seeking an experienced AI-first engineer to own the development of end-to-end AI-native features and deliver practical solutions to restaurant operators and customers. You’ll own frontend, backend, data, and model integration, shipping real products quickly on a small, fast-moving NYC team.

You’ll design and build end-to-end AI-powered capabilities, work with LLM APIs, and drive rapid iteration while collaborating with product and operations to solve real restaurant problems.