Full Stack AI Engineer

About the role

We are building a core product that transforms psychological assessment data into clinician‑grade narratives using large language model (LLM) pipelines. As a senior Full Stack AI Engineer you will design and ship production‑grade microservices that ingest data, retrieve knowledge from manuals, and generate accurate narratives for our customers.

Key responsibilities

• Architect, design, and implement scalable microservices for data ingestion, extraction, indexing, retrieval, and augmented generation.
• Build secure Python‑backed APIs that integrate with our React frontend.
• Integrate and manage LLMs, embeddings, and vector stores to ensure context‑aware narrative generation.
• Validate outputs against domain data to guarantee correct assessment classifications.
• Establish best practices for reliability, observability, CI/CD, and Git workflows.
• Deliver end‑to‑end features quickly, collaborating with Product and the Head of Engineering.
• Document system designs, runbooks, and handoff materials.
• Mentor junior engineers through code reviews and guidance.

Required profile

• Proven track record delivering end‑to‑end product features that embed AI/LLM outputs.
• Outcome‑oriented mindset, able to drive ambiguous projects to tangible results.
• Strong communication skills to translate fuzzy product vision into clear technical plans.
• Comfortable working in a fast‑moving startup environment with frequent pivots.

Required skills

• Python
• Design and implementation of microservices and APIs
• LLM integration, prompt/response engineering
• Embeddings and vector stores
• React (front‑end) development
• CI/CD pipelines
• Git workflow management
• Production observability and security practices

What we offer

• USD 2,500/month for the first 90 days, then USD 3,000/month thereafter
• Unlimited paid time off
• Fully remote work (Latin America only)