Generative AI Architect

Description

We are seeking a **Generative AI Architect** to join our team in Madrid in a hybrid work environment. The selected candidate will lead the design and implementation of generative AI-based solutions, ensuring scalability, security, and alignment with business needs. They will collaborate with multidisciplinary teams to drive innovative use cases in enterprise settings. EPAM NEORIS is a digital accelerator that supports some of the world’s leading companies in addressing business challenges and technological evolution, combining global engineering excellence with regional expertise and local proximity. With a presence in 11 Latin American and Iberian countries and over 4\.000 professionals across the region, we foster a diverse and inclusive culture focused on collaboration, continuous learning, and innovation. As part of EPAM—a global network comprising over 60\.000 professionals across 55+ countries—we help organizations scale, modernize, and accelerate their digital capabilities through Cloud, Data \& Analytics, Artificial Intelligence, Cybersecurity, Intelligent Automation, Strategic Consulting, and Software Engineering. At EPAM NEORIS, we believe growth is also built from people. Therefore, we promote an environment where every professional can develop, contribute new ideas, and participate in regionally and globally impactful projects. **Responsibilities** * Design end\-to\-end architectures for generative AI solutions, including RAG, agents, copilots, and model fine-tuning strategies * Define design patterns for using large language models (LLMs) in production environments, including prompting, orchestration, and tool calling * Implement information retrieval pipelines using embeddings, vector databases, and ranking mechanisms * Integrate generative AI solutions into products and platforms via APIs and microservice architectures * Optimize production solution performance through improvements in cost, latency, scalability, and observability * Ensure security, privacy, and regulatory compliance in the use of enterprise models and data **Requirements** * Proven experience in architecting and implementing generative AI solutions using large language models (LLMs) * Professional experience with RAG architectures and vector databases such as Pinecone, Weaviate, or similar * Advanced knowledge of orchestration frameworks such as LangChain, LlamaIndex, or equivalents * Proficiency in cloud environments—especially Azure—and distributed architectures * Demonstrable experience in MLOps or LLMOps, including model deployment, monitoring, and versioning * Solid understanding of APIs, microservices, and enterprise production systems * Minimum 5 years of experience in data, AI, or software solution architecture, including relevant generative AI experience * University degree in Computer Engineering, Telecommunications, Mathematics, Physics, or related disciplines * Professional-level English proficiency for collaboration in international environments **Nice to have** * Experience with fine\-tuning, RLHF, or model alignment techniques * Knowledge of autonomous agents and advanced tool-use patterns * Experience in LLM evaluation, guardrails, and red-teaming strategies * Familiarity with open-source models such as Llama, Mistral, or similar * Cloud certifications in Azure or AI-related specializations **We offer** * • Permanent contract with competitive salary• Flexible working arrangements and remote work options• Personalized career path and continuous training• Participation in stable, technically demanding projects• Flexible working hours and emphasis on work-life balance• Social benefits tailored to your needs