In this role you will design and scale intelligent data platforms that enable multi-agent AI collaboration to solve analytical and mathematical tasks. You will oversee the integration of LLMs, symbolic solvers, and data pipelines into production systems, balancing performance, cost, and governance. This is a chance to shape AI-enabled data platforms that improve efficiency and collaboration across the air transport ecosystem.

Flex Week: work from home up to 2 days/week Flex Day Flex-Location: up to 30 days/year remote work LinkedIn Learning and professional development Design and scale intelligent data platforms with multi-agent collaboration Build multi-agent architectures for planning, memory, tool usage and coordination Develop scalable batch and real-time data pipelines and data models supporting agent memory and retrieval (vector databases/RAG) Establish LLMOps/MLOps practices for deployment, monitoring, evaluation and testing (including mathematical correctness)



Optimize performance and cost of LLM and compute-heavy workloads; 6+ years in data engineering and/or distributed systems with hands-on delivery of production platforms Strong Python and SQL skills;

experience with data models, data quality controls and observability Experience with distributed data processing and streaming (e.g., Spark, Kafka) and cloud platforms (AWS, Azure, or GCP) familiarity with agent frameworks (orchestration, tool usage, memory) and RAG/vector databases NumPy/SciPy/SymPy, optimization libraries, symbolic/numerical engines) Understanding of security best practices and governance for data/AI platforms (IAM, secrets management, auditability) Python SQL Spark Data Scientist - Analytics and ML - barcelona • barcelona, catalunya, es

📌 Data Scientist con Spark (Barcelona)
🏢 Sita - Société Internationale De Télécommunications
📍 Barcelona