Senior AI Engineer: Production LLM & Automation (Remote)

Ruby Labs Ltd; Georgia; Remote; USD 140,000 - 190,000; Full time

Benefits offered by this job

Paid national holidays

Flexible independent contractor quiet?

Work from anywhere

Job summary

Ruby Labs Ltd is seeking a Senior AI Engineer to own and scale the AI layer of a core D2C subscription product. You’ll own production LLM features and the browser automation built around them end to end — prompts, outputs, evaluation, and observability.

Work in a modern TypeScript stack (Next.js, Cloudflare Workers, Playwright) and drive model selection, cost efficiency, and reliability. This is a high-impact role with data‑driven decisions and shipped automation as frozen, versioned workers.

Qualifications

• 5+ years of software engineering with Node.js, TypeScript, Next.js, and Postgres.
• Production experience with dynamic prompting and structured outputs in production.
• Experience with unified LLM APIs or AI gateways (OpenRouter, Cloudflare AI Gateway).
• Ability to decide on benchmarks and trace data, not intuition.

Responsibilities

• Design dynamic prompt templates with conditional logic and context injection.
• Own complex LLM workflows that integrate into application logic.
• Build and maintain browser automation on Browserbase Functions and Playwright.
• Ship automations as frozen, published workers — versioned and safe to roll back.
• Build evaluation pipelines and score responses and classifications in Langfuse.
• Run A/B experiments across models and prompts through an AI gateway.
• Resolve production incidents in owned AI and automation systems.

Skills

Node.js

TypeScript

Next.js

Postgres

Cloudflare Workers

Browser automation

Playwright

LangChain

LlamaIndex

Langfuse

OpenRouter

AI Gateways

Tools

LangChain

LlamaIndex

Browserbase Functions

Playwright

Hono

Hatchet

Drizzle

Supabase

Vercel

Next.js

Job description

Ruby Labs Ltd is seeking a Senior AI Engineer to own and scale the AI layer of a core D2C subscription product. You’ll own production LLM features and the browser automation built around them end to end — prompts, outputs, evaluation, and observability.

Work in a modern TypeScript stack (Next.js, Cloudflare Workers, Playwright) and drive model selection, cost efficiency, and reliability. This is a high-impact role with data‑driven decisions and shipped automation as frozen, versioned workers.