Junior AI Engineer

Ruby Labs

1d•Remote

About The Position

At Ruby Labs, we are building a Direct-to-Consumer product in the AI category. We’re looking for a Junior AI Engineer (Node.js / Next.js / TypeScript) to join our AI engineering team and contribute to production-ready LLM experiences. You’ll work alongside senior engineers in a modern stack, learning to make data-driven decisions around model performance, reliability, and cost. You’ll contribute to prompt systems, structured outputs, and LLM workflows while building familiarity with observability and evaluation tooling like Langfuse and AI gateways like OpenRouter. This is a hands-on role where you will grow quickly by shipping real AI features to production under the guidance of experienced teammates.

Requirements

0–2 years of software engineering experience — recent graduates, bootcamp graduates, and early-career engineers are welcome.
Working knowledge of Node.js, Next.js, and TypeScript.
Basic understanding of how LLMs work and hands-on experience using LLM APIs (OpenAI, Anthropic, or similar).
Experience writing prompts that go beyond simple instructions, such as using variables, templates, or conditional logic.
Familiarity with structured outputs (JSON mode, function calling, or schema validation).
Understanding of basic web application architecture, RESTful APIs, and backend fundamentals, including request validation, error handling, and logging.
Curiosity and willingness to learn quickly in a fast-moving AI product environment.
Strong communication skills and a collaborative mindset.

Nice To Haves

Experience with AI-centred development tools (Cursor, Claude Code, Windsurf, or similar).
Experience with LLM observability tools (Langfuse, LangSmith, or similar).
Exposure to AI gateways such as OpenRouter or model routing concepts.
Exposure to AI agents, tool use/function calling, or the Model Context Protocol (MCP).
Familiarity with evaluation frameworks (RAGAS, custom LLM-as-a-judge systems).
Familiarity with LLM orchestration frameworks (LangChain, LlamaIndex) or RAG concepts.
Familiarity with Python (e.g., for evaluation or data scripts).
Experience with Redis or real-time data systems.
Experience working in startup or fast-paced product environments.

Responsibilities

Implement AI-powered product features and workflows based on specifications from senior engineers.
Write, iterate on, and manage production prompt templates following established patterns for dynamic prompting and context injection.
Participate in prompt experimentation workflows by drafting variants, running A/B tests across models via OpenRouter, and documenting results.
Integrate structured output schemas (JSON mode, function calling, Zod/JSON schemas) to ensure AI responses are predictable and application-ready.
Build and maintain output enforcement mechanisms such as validators and repair loops under senior guidance.
Help implement tool calling and function calling integrations so AI features can fetch data or trigger actions, following patterns established by senior engineers.
Contribute to evaluation pipelines and help assess prompt and model quality using Langfuse.
Write clean, maintainable TypeScript code within the Next.js and Node.js stack.
Participate in code reviews and incorporate feedback.
Document technical decisions and system behaviour to support knowledge sharing.
Collaborate with product, growth, data, and billing teams to deliver features on time.