**\#JoinLuby** ---------------- **Here’s what you’ll get to do:** * **Grow in a high-performance environment:** A culture where continuous development is the norm — with autonomy and involvement in national and international projects that truly challenge your skills and unlock your potential. * **Join a technology-passionate team:** You’ll collaborate alongside experienced professionals in a collaborative and disruptive environment, leveraging the most advanced technologies in the market. * **Make your mark on the world:** Our digital solutions directly impact the lives of thousands of people — and this is your chance to actively shape a more digital and connected future. * **Work remotely and flexibly:** No matter where you are, we’re ready to welcome you onto our team! **Your Mission:** We’re looking for a Senior AI Engineer to build an end-to-end Retrieval-Augmented Generation (RAG) pipeline — from retrieval and generation to delivering structured outputs in BigQuery. You’ll be responsible for ensuring response quality, defining technical excellence standards, and working directly on Google Cloud using the most modern GenAI tools. You’ll play a key role in designing intelligent solutions, collaborating closely with product teams to build robust, production-ready AI systems. **Key Responsibilities:** * Own the end-to-end RAG pipeline — leading ingestion, chunking, embeddings, retrieval, and response generation. * Design, build, and optimize vector search using vector databases. * Define and execute model quality evaluation routines (relevance, grounding, and hallucination detection), continuously iterating to improve results. * Structure and ensure delivery (landing) of generated data into structured BigQuery tables. * Design integrations with multiple data sources using MCP (Model Context Protocol) and OneSource. * Operationalize Machine Learning (ML) workflows on Vertex AI / GCP — implementing CI/CD pipelines, monitoring, and ensuring reproducibility. * Partner closely with Product Owners and stakeholders to guide technical and architectural product decisions. **Essential Requirements:** * Senior-level hands-on Python development experience. * Practical (hands-on) experience building RAG solutions: embedding creation, vector search, retrieval tuning, and prompt design & generation. * Proven experience deploying and operating GenAI and LLMs in production environments. * Solid hands-on experience with vector databases. * Practical knowledge of integrations using MCP (Model Context Protocol). * Experience with data ingestion and consolidation processes in BigQuery. **Nice-to-Have:** * Advanced expertise across the Google Cloud ecosystem (BigQuery, Vertex AI, Cloud Composer, Dataflow). * Experience with conversational AI (Dialogflow), BI tools (Looker), agent-based AI, or knowledge graphs/ontologies. * Prior use of RAG evaluation frameworks (e.g., LLM-as-a-judge). **What We Offer:** * **Remote Work:** Enjoy the flexibility to work from anywhere in Brazil — with full autonomy and self-organization. * **Health & Well-being:** Health and dental insurance, life insurance, and Wellhub (Gympass). * **\+Education:** Discounts on FIAP courses and USP Esalq MBA programs — so you can keep learning and growing. * **Exclusive Perks:** Discounts at Multilaser stores, referral bonuses for professionals and business leads, adaptable working hours, and annual bonus. ### ***Learn more about our culture, benefits, and what it’s like to be a \#Luber on our*** ***Careers Page!***
João Silva
Indeed · HR
João Silva
Indeed · HR
