Senior AI Engineer - Remote, Unlimited PTO, Production LLM

Ruby Labs Ltd; Atlanta (GA); Remote; USD 150,000 - 210,000; Full time

Benefits offered by this job

Remote Work Environment

Unlimited PTO

Paid National Holidays

Company-provided MacBook

Flexible Independent Contractor Allow.

Job summary

Ruby Labs Ltd. seeks a Senior AI Engineer to own and scale the AI layer of a core D2C subscription product. You will lead production LLM features, structured outputs, and browser automation end-to-end—from experiments to live release—with emphasis on quality, reliability, and cost.

You will work in a modern TypeScript stack (Next.js, Cloudflare Workers, containers) and own prompts, evaluation, and model selection while ensuring safe and scalable automation across Browserbase and Playwright.

Qualifications

• 5+ years of software engineering with Node.js, TypeScript, Next.js, and Postgres.
• Production browser automation with Playwright at scale.
• Experience with dynamic prompting and structured outputs in production.
• Structured outputs using JSON mode, function calling, and JSON schemas.
• Familiarity with unified LLM APIs or AI gateways and observability tools.
• Experience with evaluation and benchmarking of models.

Responsibilities

• Own AI features from experiment to production on Cloudflare Workers and containers.
• Manage rate limits, fallbacks, and model cost for reliability at scale.
• Resolve production incidents with root-cause analysis.
• Design dynamic prompts and ensure JSON structured outputs in production.
• Build and maintain browser automation to traverse complex web flows.
• Lead evaluation pipelines and track cost, latency, and context usage.

Skills

Node.js

TypeScript

Next.js

PostgreSQL

Cloudflare Workers

Playwright

JSON schemas

LangChain

LLM observability

Tools

Browserbase

Hatchet

Drizzle

Supabase

Vercel

Langfuse

OpenRouter

Cloudflare AI Gateway

LlamaIndex

Job description

Ruby Labs Ltd. seeks a Senior AI Engineer to own and scale the AI layer of a core D2C subscription product. You will lead production LLM features, structured outputs, and browser automation end-to-end—from experiments to live release—with emphasis on quality, reliability, and cost.

You will work in a modern TypeScript stack (Next.js, Cloudflare Workers, containers) and own prompts, evaluation, and model selection while ensuring safe and scalable automation across Browserbase and Playwright.