AzureCloudDockerETLGoogle Cloud PlatformLinuxNoSQLPythonRPASparkSQLAIMachine LearningLarge Language ModelsOpenAIGeminiLlamaRAGLangChainLlamaIndexAgenticMLOpsMLflowDatabricksGCPGoogle CloudServerlessGitGitHubPerformance OptimizationCollaborationRemote Work
About this role
Role Overview
Designing and implementing AI solutions aligned with business needs and technological standards.
Applying techniques like Retrieval-Augmented Generation (RAG) to improve precision and relevance of AI interactions.
Developing Agentic RAGs, incorporating autonomous agents to refine data retrieval and content generation.
Creating modular architectures for agents specializing in tasks like information retrieval and contextual inference.
Leveraging Large Language Models (LLMs) for text generation and question answering.
Designing and managing data ingestion pipelines and implementing serverless architectures.
Using DevOps and MLOps practices for automating deployment and management of AI models.
Integrating APIs to connect AI models with external systems and to register events and metadata.
Performance optimization including analyzing system performance and detecting bottlenecks.
Requirements
Advanced Python development skills.
Proven experience with Hybrid AI / RAG architectures and state-of-the-art LLMs (commercial: OpenAI, Gemini; open-source: Llama 2, Mistral).
Hands-on experience with orchestration frameworks such as LangChain, LlamaIndex, Rasa, or Haystack.
Strong understanding of classical Machine Learning for prediction and anomaly detection.
Experience with Docker, Linux, and hybrid cloud environments (Azure, GCP) including on-prem deployments.
Proficiency in SQL and NoSQL databases, with focus on optimization and data retrieval for RAG and model pipelines.
Strong background in API design and integration (REST), including data anonymization/encryption, authentication, and access control.
Familiarity with MLOps tools and practices (Git/GitHub, MLflow or equivalents) for versioning, tracking, and monitoring models.
Understanding of data quality, governance, and reporting (KPIs) within AI solutions.
Experience with Azure Databricks for scalable data processing, model training, and deployment workflows (ETL, Spark, Delta Lake, MLflow integration).
Experience with Azure Purview for data cataloging, governance, lineage, and ensuring compliance (GDPR, data classification, policies).
Excellent collaboration skills and ability to deliver quick, high-impact solutions across teams.
(Nice to have) Experience in RPA and process automation, e.g., Power Automate.
Tech Stack
Azure
Cloud
Docker
ETL
Google Cloud Platform
Linux
NoSQL
Python
RPA
Spark
SQL
Benefits
Remote work, with occasional on-site presence in Alcorcón due to client requirements
Flexible hours
Special timetable: Fridays and summer 7h.
Individual budget for attending forums and training