AI Software Engineer (GenAI / LLM)

Description

**Company Description** ----------------------------- Why work at Sopra Steria? Because it also means *feeling* Sopra Steria. We are a renowned European leader in consulting, digital services, and software development, with nearly 56,000 employees across almost 30 countries—and over 4,000 in Spain. We focus on people—on their training and professional development—which drives our constant growth and improvement. We are passionate about digital transformation, and like you, we seek the best adventure. We want your everyday work to become your greatest source of inspiration: to learn, contribute, have fun, grow—and above all—to enjoy it to the fullest. If you want to join a "**Great Place to Work**" team, keep reading! **Job Description** -------------------------- We are looking for an **AI Software Engineer (GenAI / LLM)** to join our team and participate in an international project within the insurance sector. You will be responsible for designing, developing, and deploying AI-based solutions built with Anthropic Claude. Working within cross-functional agile teams, you will design and implement applications that leverage large language models (LLMs) to solve real business problems. Your work will span the entire development lifecycle—from translating business requirements into prompting strategies and system architectures, to deploying, monitoring, and continuously improving AI systems in production. You will assume end-to-end ownership of AI capabilities and play a key role in defining the organization’s best practices for AI engineering. * Collaborate with product owners and agile team members to understand business requirements and translate them into AI-driven solutions. * Evaluate use cases based on Claude’s suitability and design effective prompt architectures, RAG pipelines, and agent workflows. * Design, implement, and iterate prompts and system instructions to achieve reliable, high-quality model outputs. * Develop and maintain integrations with the Claude API, including multi-turn conversations, tool usage, and structured output generation. * Apply advanced prompting techniques such as chain-of-thought reasoning, few-shot learning, and context management strategies. * Build production-ready AI applications and services (REST APIs, backend services, AI agents) that integrate Claude into existing or new systems. * Implement retrieval-augmented generation (RAG) architectures—including document ingestion pipelines, vector database management, and semantic search. * Develop tool-use integrations and function-calling mechanisms enabling Claude to interact with external systems and APIs. * Ensure robustness through error handling, fallback strategies, output validation, and controlled degradation. * Design and implement evaluation frameworks to measure model performance, accuracy, and consistency across different use cases. * Write unit, integration, and end-to-end tests for AI-driven features—including LLM output validation strategies. * Monitor deployed AI systems for quality, latency, cost, and security; and implement alerting and observability tools. * Contribute to CI/CD pipelines for AI applications—including automated evaluation and regression detection. * Apply responsible AI principles in system design—including safety filters, bias assessment, and alignment with Anthropic’s usage policies. **Requirements** -------------- **What do we need?** * 5 years of experience in Software Engineering, with at least 1 year directly working with LLM APIs (Claude, OpenAI, or equivalents) in production environments. * Prompt engineering and LLM application development—including system prompt design, context management, tool usage, and multi-turn conversation handling. * Solid software engineering fundamentals: RESTful API development, clean coding practices, version control (Git), and CI/CD pipelines in at least one primary language (preferably Python). * Familiarity with the AI/ML ecosystem: vector databases, embedding models, RAG architectures, and LLM evaluation frameworks. * Responsible AI: understanding of AI safety concepts, output validation, risk mitigation strategies, and considerations for ethical deployment. * Proven ability to take AI features from prototype to production—including performance optimization, monitoring, and iterative improvement. Experience in agile environments and strong communication skills to engage both technical and non-technical stakeholders. * Advanced English (B2+/C1). **Additional Information** ------------------------- **What do we offer?** * Permanent contract and full-time schedule * 23 vacation days * Flexible hybrid remote work model * Continuous training: technical, soft, and language skills. Access to certifications, trainings from leading Technology Partners, online platforms—and much more! * Life and accident insurance * Option to enroll in our flexible compensation plan (health insurance, childcare vouchers, transport, meal vouchers, and training) * Access to Privilege Club, offering attractive discounts with top brands * Personalized and detailed onboarding. We support you every step of the way so you feel \#soprano from day one. * Office with dedicated leisure spaces—where work and fun come together! * Camaraderie and a positive atmosphere—we truly believe in the power of unity. And most importantly…you’ll have the opportunity to develop your professional career with us: Together, we’ll create a personalized career plan. You’ll receive training, set goals, and undergo regular follow-ups to ensure we achieve them—together. We listen to your priorities—and fight for them. Your voice matters here! Join us and be part of something greater! **The world is how we shape it** At Sopra Steria, we are committed to building a diverse and inclusive environment, evaluating each candidate objectively based on competencies and experience. We firmly believe that diversity of experiences and perspectives is what fuels our innovation.