Lead Data Platform Engineer (Huelva)
9 hours ago
Huelva
ph3Role Description /h3pWe are seeking an expert with deep proficiency as a Palantir Platform Engineer, possessing experience in data engineering and designing, building, and operationalizing AI‑powered workflows, agents, and applications that drive tangible business outcomes. The adecuado candidate is a self‑starter, able to translate complex business needs into scalable technical solutions, and confident working directly with stakeholders to maximize the value of Foundry and AIP. /ph3Responsibilities /h3ulliManage and optimize Palantir data platform. /liliEnsure high availability, security, and performance of data systems. /liliProvide valuable insights about data platforms usage. /liliOptimize computing and storage for large-scale data processing. /liliDesign and maintain system libraries (Python) used in ETL pipelines and platform governance. /liliOptimize ETL Processes – Enhance and tune existing ETL processes for better performance, scalability, and reliability. /liliAIP AI Enablement: Support the design and deployment of AIP use cases such as copilots, retrieval workflows, and decision-support agents. /liliGround agents and logic flows using RAG (retrieval‑augmented generation) by connecting to relevant data sources, embedding/vector search, ontology content. /liliUse Ontology-Augmented Generation (OAG) when needed: operational decision‑making where logic, data, actions and relationships are embedded in the Ontology. /liliCollaborate with senior engineers on agent design, instructions, and evaluation using AIP's native features. /li /ulh3Skills /h3h3Must have /h3ulliMinimum 10 Years of experience in IT/Data. /liliMinimum 5 years of experience as a Data Platform Engineer/Data Engineer. /liliMinimum 3 years of experience with Palantir Foundry. /liliPractical experience using or supporting AIP features such as RAG workflows, copilots, or agent‑based applications. /liliBachelor's in IT or related field. /liliInfrastructure Cloud: Azure, AWS (expertise in storage, networking, compute). /liliProficiency in PySpark for distributed computing. /liliProficienc /li /ul /p #J-18808-Ljbffr