Senior AI/LLM Engineer - Remote LATAM

Reunion Marketing South America Remoto Publicada em 23 de jun. de 2026

Senior

A descrição completa está disponível na vaga original.

Responsabilidades

Design and own the full LLM pipeline from raw data and strategy documents to client-ready summaries, alerts, and recommendations
Design the retrieval system that grounds the model in Reunion's strategy library, product data, client history, and market context
Design and ship multi-step reasoning workflows behind Monthly and quarterly AI Client Summaries, Opportunity identification, Market re-evaluation, Inventory and sales alignment, At-risk account flagging, and Anomaly explanation and routing
Stand up and operate MCP servers that expose Reunion's knowledge and client context to the reasoning engine
Build the evaluation system end-to-end including offline experiments, regression suites in CI, online scoring of production traces, factuality checks, and structured output validation
Help design how strategists review, edit, approve, regenerate, or reject AI-generated outputs
Own the hard parts of production LLM systems: hallucinations, retrieval misses, tool-use failures, structured-output drift, prompt drift, schema changes, cost spikes, latency regressions
Make clear, evidence-backed architectural calls on prompting vs. RAG, RAG vs. GraphRAG, tool-use vs. direct generation, fine-tuning vs. better retrieval

6+ years of software engineering experience, with 2+ years shipping production LLM systems with real consequences when they break
Strong in a modern application language used for production LLM systems — TypeScript/Node, Python, or both
Deep, hands-on familiarity with prompt design and structured output generation
Retrieval architecture experience — vector, lexical, hybrid, reranking, freshness, multi-tenant scoping
Tool-use and agent design experience — when to use one, when not to
Evaluation as an engineering discipline (offline + online + regression gating)
Production experience with knowledge graphs (Neo4j or comparable) for entity resolution, multi-hop reasoning, GraphRAG, or relationship-rich domain modeling
Has designed and shipped an evaluation suite that caught a real regression in production
Production debugging instincts for LLM failures with specific failure modes fixed
Durable workflow orchestration in production — Inngest, Temporal, Step Functions, Airflow, or similar
MCP or equivalent tool-use surface in production
Track record of owning the quality bar on a multi-team AI product including incident response and rollbacks
Strong written and architectural communication

O JobMode.app diz se a vaga combina com você, estima a faixa salarial, adapta seu currículo e escreve respostas de triagem — direto no navegador.