20 days ago
Madrid, SpainMid Level / Senior
Responsibilities
- Design and develop cloud-based AI applications and services integrating LLMs and generative AI capabilities.
- Build backend REST and GraphQL services, microservices, and integrations with internal and external APIs.
- Develop RAG pipelines covering ingestion, chunking, embeddings, vector storage, and retrieval.
- Build agents with LangChain, LlamaIndex, Semantic Kernel, or comparable orchestrators, including tool and function calling.
- Implement CI/CD, containerization, quality gates, testing, observability, and API security controls.
- Apply LLMOps/MLOps practices including prompt and artifact versioning, evaluation, monitoring, cost tracking, drift detection, and guardrails.
- Collaborate with architecture, data, security, and business teams on scalability, resilience, cost, governance, compliance, and AI ethics.
- Document architecture decisions, create reusable playbooks and accelerators, review code, and mentor junior engineers.
Requirements
- 3–7+ years of software engineering experience, depending on seniority, including API design, integration patterns, concurrency or asynchronous programming, and strong coding practices.
- Professional experience with Python and backend frameworks such as FastAPI, Flask, or Express.
- Advanced Git experience and experience with CI/CD using GitHub Actions, GitLab CI, Azure DevOps, or Jenkins.
- Experience with at least one major cloud platform—Azure, AWS, or GCP—and containerized workloads using Docker; Kubernetes is desirable.
- Practical experience integrating generative AI and LLM services, including API consumption, authentication, cost and limit management, prompting, and basic evaluation.
- Practical knowledge of RAG, embeddings, vector stores, and orchestration frameworks such as LangChain, LlamaIndex, or Semantic Kernel.
- Experience with unit, integration, or contract testing; monitoring such as OpenTelemetry; and basic API security including OAuth2/OIDC, secrets, and rate limiting.
- Experience with LLMOps/MLOps tools and practices, including MLflow, Weights & Biases, Prompt Flow, Azure AI Studio evaluations, experiment tracking, and evaluation dashboards.
- Professional English proficiency and clear communication, documentation, collaboration, and continuous-learning skills.
- Preferred experience includes Terraform, advanced Kubernetes, event-driven systems using Pub/Sub or Kafka, SLO/SLA practices, alerting, chaos testing, GenAI security and compliance, and agentic AI.
Benefits
- Hybrid work model with flexibility and a culture focused on work-life balance.
- Training, online and in-person learning, and professional certifications.
- Exposure to varied, multisector projects involving generative AI, Business AI, cloud, data governance, and emerging technologies.
- Collaborative, inclusive, multicultural teams and opportunities for mentoring and professional growth.
- Technical challenge, autonomy, and opportunities to expand responsibilities within the Data & AI area.
Tech Stack
Apache KafkaAWSAzureDockerExpressFastAPIFlaskGitGitHub ActionsGitLab CI/CDGoogle Cloud PlatformGraphQLJenkinsKubernetesMLflowPythonTerraform
Categories
About Capgemini
Capgemini is a global IT services and consulting firm that delivers strategy, cloud, AI, software engineering, and managed services to large enterprises and public-sector clients. Founded in 1967 and headquartered in Paris, it is publicly traded on Euronext Paris and operates in 50+ countries. The group expanded its engineering capabilities by acquiring Altran in 2020, now operating as Capgemini Engineering.