**#JoinLuby** ---------------- **Here’s what you’ll get to do:** * **Grow in a high-performance environment:** A culture where development is continuous, with autonomy and involvement in national and international projects that truly challenge your skills and unlock your potential. * **Join a team passionate about technology:** You’ll work alongside experienced talent in a collaborative and disruptive environment, using 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 to our team! **Your Mission:** We’re looking for a Senior Data & ML Engineer to work on the intelligence layer of an AI product applied to healthcare—responsible for transforming large volumes of clinical data: documents, lab results, prescription histories, referral letters, and electronic health record entries—into accessible, accurate, and trustworthy knowledge for intelligent agents. Unlike a centralized data platform role, this position is embedded within the intelligence team, where data engineering and ML engineering reside in the same hands: you own both the movement and structure of the data *and* the behavior of models in production. The separation between these two domains is the enemy—here, they integrate seamlessly. This person will serve as the technical peer to the Staff Engineer of the intelligence layer, in a high-engineering-standard environment with strong emphasis on production ML: versioned models, monitored pipelines, and quality regressions that trigger automatic rollback. Work rigorously respects healthcare-sensitive data constraints (PHI), cloud sovereignty requirements, and the high degree of clinical accuracy demanded by the domain. **Key Responsibilities:** * Design and maintain data ingestion pipelines for structured data (HL7/FHIR feeds, lab results, billing records) and unstructured data (fax documents with 96%+ match accuracy, clinical notes, referral letters) into the retrieval and reasoning stack; * Develop and maintain feature engineering and embedding pipelines for RAG: chunking strategies, selection and evaluation of embedding models, vector index management in Vertex AI Vector Search, and retrieval quality metrics (MRR, NDCG, precision@k); * Build and maintain model behavior monitoring stack: distribution shift detection, retrieval quality tracking, and output quality metrics aligned with evaluation suites; * Collaborate with the Agent Platform team on MLOps: model versioning, A/B routing in Vertex AI, quality-regression-triggered rollback, and experiment tracking; * Ensure secure handling of sensitive data (PHI) across all layers: pseudonymization, PHI proxy integration, enforcement of data residency in GCP/Vertex AI, and access audit log pipeline; * Maintain Knowledge Graph data quality standards, with ingestion pipelines that encode clinical domain knowledge as queryable and auditable inputs; * Evaluate and integrate new data sources as the healthcare ecosystem expands (pharmacy data, claims adjudication, patient engagement signals). **Essential Requirements:** * 8+ years of experience in Data Science or ML Engineering, with 3+ years independently leading ML projects in production; * **Fluent English;** * Solid data engineering fundamentals: pipeline design, schema management, data quality monitoring, and scalable production ETL/ELT; * Proven experience in ML Engineering—models successfully deployed to production, with clear understanding of the difference between research accuracy and production reliability; * Experience with RAG architecture: chunking strategies, embedding model evaluation, vector databases (Vertex AI Vector Search, Weaviate, Pinecone or equivalents), and retrieval quality evaluation; * Fluency in GCP/Vertex AI: BigQuery, Cloud Storage, Vertex AI Pipelines, Model Registry, and managed embedding endpoints; * Experience handling PHI or strong knowledge of Canadian privacy legislation (PIPEDA/PHIPA), treating privacy as a design constraint—not an afterthought; * Proficiency in Python (primary language of the data and ML stack); * Experience with RAG and MLOps is mandatory; * Education: Master’s degree in Computer Science, Data Science, or equivalent experience and certifications; * GCP Machine Learning Engineer certification (or equivalent cloud-based ML certification). **Nice-to-Have:** * Experience with clinical data formats: HL7 v2/v3, FHIR R4, ICD-10, SNOMED CT, and drug coding systems (DIN, NPN); * Familiarity with Canadian data residency requirements and provincial variations in health privacy laws (Ontario PHIPA, Quebec Law 25, etc.); * Experience with knowledge graph data models: RDF, property graphs, and clinical ontologies; * Experience with MLflow, Kubeflow, or Vertex AI Pipelines for experiment tracking and pipeline orchestration. **What We Offer:** * **Remote Work:** Enjoy the flexibility of working 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 to 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, perks, and what it’s like to be a #Luber on our*** ***Careers Page!***
João Silva
Indeed · HR
João Silva
Indeed · HR
