AI Engineer

360Learning

21h•Remote

About The Position

AI is central to 360Learning's strategy: our AI Squad ships agentic features that help users discover, create, and administrate content. As an AI Engineer, you'll architect and ship the next generation of these AI systems, from prototype to production. You will join the AI Squad as its second AI Engineer, working closely with 1 peer AI Engineer, 1 Product Manager, 1 Product Designer, and 4 Full-Stack Developers. You will own the technical strategy for AI features while collaborating directly with product, design, and engineering. Over the last year, we have shipped 5+ AI features powering thousands of users monthly: Catalog Companion: An AI agent performing bulk catalog operations (sharing, archiving, tagging, author assignments) Smart Search: conversational search helping users discover the right content Conversational BI : Analytics and insights delivered through natural conversation AI Course & Question Generation: Creating questions and full courses from documents and titles Content Recommendations: Personalized content discovery Our squad is unique because we operate in one of the fastest-moving fields in tech: AI! Within 1 month, you will: Graduate in Convexity through our onboarding process Understand our product offering through training Meet the team through virtual coffee meets and happy hour Learn our processes and tools Get a global view of our codebase and architecture (Pydantic AI, FastAPI, Azure OpenAI, ElasticSearch) Contribute meaningfully to an existing feature Own end-to-end delivery of a new AI feature: from technical design through production launch Optimize for real-world constraints: reduce per-request costs, improve latency, scale to handle usage spikes Make architectural decisions as we scale from 5 to 10+ features Prototype and ship advanced capabilities: new modalities, real-time collaboration Be the technical authority from your peer

Requirements

2 years of experience taking GenAI / LLM-powered systems from prototype to long-term production deployment
Strong Python experience, with a track record of clean, maintainable production code
Hands-on experience integrating LLM (Azure OpenAI, OpenAI, Anthropic, Mistral, etc.) and managing real-world constraints: token costs, latency, reliability, hallucinations
Familiarity with Search capabilities, RAG, semantic search, vector databases
Agents
LLM observability tools (Langfuse or similar)
Evaluation of models
Solid grasp of Machine Learning fundamentals (evaluation, experimentation, model lifecycle)
Fluent English (US/UK) / B2 level or equivalent (FR)

Responsibilities

Own end-to-end delivery of a new AI feature: from technical design through production launch
Optimize for real-world constraints: reduce per-request costs, improve latency, scale to handle usage spikes
Make architectural decisions as we scale from 5 to 10+ features
Prototype and ship advanced capabilities: new modalities, real-time collaboration