Job Summary: We are seeking a Senior AI Platform Backend Engineer (LLM) for an innovative project in AI platforms, LLM-as-a-Service, AI-generated content verification, and advanced RAG solutions. Key Highlights: 1. Highly innovative project on AI platforms 2. Role combining advanced backend, MLOps, DevOps, and Cloud 3. Research-oriented mindset with results-driven approach #### **Job Description** At **The Whiteam Consulting**, we are looking for a **Senior AI Platform Backend Engineer (LLM)** to join a highly innovative project in the field of AI platforms, LLM-as-a-Service, AI-generated content verification, and advanced Retrieval-Augmented Generation (RAG) solutions. The role combines advanced Python backend development, MLOps, DevOps, cloud (AWS/Azure), model optimization, and deployment of multi-service architectures on Kubernetes. We seek a senior-level, autonomous professional with a research-oriented mindset, results-driven approach, and hands-on experience in LLM-based architectures (OpenAI, Anthropic, Google), production-grade RAG, AI pipelines, and distributed services. The ideal location is **Barcelona**, though candidates across Spain are welcome, provided they are available for occasional travel to the client. #### **Responsibilities** * Design, implement, and manage cloud infrastructure on **AWS**, using IaC (**Terraform, CloudFormation**). * Maintain and enhance **CI/CD** pipelines using GitHub Actions, AWS CodePipeline, Jenkins, or ArgoCD. * Implement observability systems using **CloudWatch, Prometheus/Grafana, ELK, or OpenTelemetry**. * Manage and operate services on **Kubernetes (EKS)**, ECS, or Fargate. * Develop backend architecture for **AI Verification and ChatGPT-like services** using **Python and FastAPI**. * Design and build solutions following **DDD** and **TDD**. * Develop **LLM-as-a-judge** services using HuggingFace, Transformers, SpaCy, NLTK, BM25. * Optimize latency using **ONNX**, quantization, and other compression techniques. * Deploy and maintain multi-service AI solutions on Kubernetes with advanced observability. * Build CI/CD pipelines for continuous deployment of AI microservices. * Design and maintain high-load RAG solutions: + Data ingestion + Messaging brokers + Retrieval services + Integration with agent-like tools (LangChain, Unstructured) + Azure OpenAI, Embeddings, Azure Cosmos DB, Service Bus, App Services * Perform advanced **prompt engineering** (Chain-of-Thought, few-shot learning, multi-LLM). * Evaluate new architectures, agents, and solutions from various cloud providers. * Analyze security, modularity, and scalability of AI-based architectures. #### **Requirements** * **5+ years** designing and implementing cloud solutions on **AWS** (Azure experience highly valued). * Experience with IaaS, PaaS, serverless, and distributed architectures. * Proficiency in **Kubernetes**, microservices, and IaC (**Terraform**). * Hands-on experience with **MLOps**, ML pipelines, and **LLM-based solutions** (chatbots, RAG, agents, LLM-as-a-Service). * Strong backend development skills with **Python** and **FastAPI**. * Experience with Prometheus, Grafana, ELK, or OpenTelemetry. * Experience designing and deploying **RAG** systems and agent-based architectures. * In-depth knowledge of **CI/CD** and DevOps practices. * Experience deploying cloud-native services on **AWS or Azure**. * Familiarity with model optimization (ONNX, quantization). * Experience working in **Agile (Scrum)** environments. * **C1 English**. * Autonomous, proactive, and results-driven profile. #### **Desirable** * Knowledge of **Cloud Security** and compliance. * Experience with cloud cost-optimization tools. * Experience in advanced automation and complex workflows. * Experience in international projects and multi-team ecosystems. #### **Work Mode** * Ideal: **Barcelona (occasional on-site presence)**. * Alternative: **Candidates based in Spain with availability for occasional client travel**. **Company** Joining THEWHITEAM means collaborating with a company composed of professionals with extensive experience in technology consulting. We firmly believe that enterprises and clients define the direction of the industry, but people build it. We consider it vital that our organization rests upon our most valuable asset and differentiator — our human team. **Benefits** Additionally, here’s a brief summary of our company policies to help you get to know us better: * Our collective agreement is that of Consulting Firms and Market Research Agencies * 23 vacation days per year * 14 monthly payments: 12 regular + 2 extra (June and December) * Flexible compensation options include childcare vouchers and medical + dental insurance.
David Muñoz
Indeed · HR
David Muñoz
Indeed · HR
