Full Stack with Deep AI coding experience (LATAM / Europe - Remote)

Senior AI/LLM Engineer role at Reunion Marketing's Altitude Intelligence, owning the LLM application layer for chat, reports, and analysis. The role involves building production LLM systems with real consequences, requiring deep experience in LLM stack, retrieval architecture, and evaluation. The engineer will own the answer pipeline, retrieval architecture, generation workflows, and evaluation discipline.

• The answer pipeline — from question or scheduled trigger, through data retrieval and reasoning, to a grounded, client-safe artifact
• Retrieval architecture — a hybrid retrieval problem spanning relational product data, client history, and our Knowledge Vault
• Generation workflows — the multi-step flows behind report and analysis generation
• Evaluation as an engineering discipline — we run large structured evaluation banks against live data and gate releases on them
• Production reliability — hallucinations, retrieval misses, tool-use failures, output drift, cost spikes, model deprecations, and the rollbacks that follow
• Architectural judgment — prompting versus retrieval versus tool-use versus fine-tuning, human review versus automated release, iteration speed versus client-safe controls

• 6+ years of software engineering experience, including 2+ years shipping production LLM systems that were customer-facing
• Strength in a modern application language used for production LLM systems
• Deep, hands-on familiarity with the LLM stack: prompt design and structured outputs; retrieval architecture (vector, lexical, hybrid, reranking, multi-tenant scoping); tool-use and agent design, including when not to use them; evaluation offline, online, and as a regression gate; and a defensible position on fine-tuning, including when to avoid it
• An evaluation suite you designed that caught a genuine regression in production
• Production debugging instincts for LLM failures
• A record of owning the quality bar on a multi-team AI product
• Strong written and architectural communication
• Nice to have: Production experience with Anthropic Claude specifically
• Nice to have: Multi-tenant client data and the access-control patterns that come with it
• Nice to have: Domain experience in marketing analytics, SEO/SEM, paid media, local search, or answer-engine visibility
• Nice to have: Experience building a system of record that an organization runs on, rather than a feature inside one