S

Santander

Global retail and commercial banking group

Frontier Agentic AI Engineer

AI Application EngineeringConfirmed live in the last 24 hours
Full-timeMadrid, Spain

About the Job

Requirements

  • At least 4–8 years of software engineering or AI engineering experience, including at least 2 years building and maintaining LLM-powered systems in production environments.
  • Hands-on experience designing and deploying complex multi-agent AI systems with memory management, stateful orchestration, tool use, multi-step planning, and graceful failure recovery.
  • Experience fine-tuning or adapting language models using SFT, LoRA, or RLHF for domain-specific tasks, including dataset curation and evaluation design.
  • Track record of independently delivering complete systems within tight timelines, from architecture decisions through production-ready code; a portfolio of real systems rather than demos.
  • Experience building and consuming REST APIs and integrating AI systems with enterprise data sources, cloud services, and third-party platforms.
  • Bachelor’s or master’s degree in Computer Science, Software Engineering, Mathematics, Physics, or an equivalent technical field.
  • Professional working proficiency in English and Spanish.
  • Advanced proficiency in Python, including clean, tested, production-grade code.
  • Experience designing multi-agent workflows with an agentic AI framework such as LangGraph, AutoGen, CrewAI, or Semantic Kernel.
  • Experience with LLM APIs and model ecosystems, including Anthropic Claude API, OpenAI, and open-source models such as Llama and Mistral, and understanding of cost, latency, and quality trade-offs.
  • Experience deploying and monitoring AI systems in cloud infrastructure, particularly AWS services such as Bedrock, Lambda, SageMaker, and S3.
  • Experience designing model evaluations and observability, using tools such as LLM-as-judge, RAGAS, Promptfoo, Langfuse, or equivalent.
  • Experience building production-ready APIs using FastAPI or an equivalent tool.
  • Knowledge of Docker, Git, and CI/CD pipelines.
  • Ability to work autonomously, propose priorities, and take ownership of what to build.
  • Ability to build proofs of concept, deliver functional demos within two weeks, and judge when a prototype is ready to transfer or needs further work.
  • Ability to explain complex agentic architectures to business stakeholders and write technical one-pagers for bank leadership.
  • Ability to give and receive direct technical feedback and document technical decisions.

Responsibilities

  • Design, build, and deploy production-grade agentic AI systems, including multi-agent orchestration with memory, planning, tool use, and error recovery.
  • Develop and fine-tune small and medium language models for regulated banking use cases, including custom evaluation frameworks and domain-specific benchmarks.
  • Architect and implement MCP servers, A2A protocols, and federated API layers that enable AI agents to operate across the group’s multi-country infrastructure.
  • Prototype ideas in two-week sprints, from hypothesis and architecture through code, functional demo, and one-pager.
  • Collaborate with researchers, data scientists, and business stakeholders to translate complex technical concepts into tangible bank value and transform legacy assets.
  • Monitor emerging research, evaluate new tools including Harness Engineering, Kiro, Windsurf, and Devin, and integrate tools into the lab’s workflow when they add value.
  • Produce clean, tested, observable code that can be handed off to the AI Science team for production scaling, owning the code end-to-end.

Desired Qualifications

  • Prior experience in banking, fintech, or another regulated industry.
  • Exposure to Harness Engineering methodologies, including spec-driven development and AI-assisted software creation at scale.
  • A master’s degree or equivalent advanced qualification in AI, Machine Learning, or a related discipline.
  • Experience with MCP server design and implementation.
  • Experience with SLM fine-tuning pipelines such as vLLM, Ollama, or Unsloth, or equivalent tools for efficient domain adaptation.
  • Experience with knowledge graphs or GraphRAG for structured knowledge retrieval in complex domains.
  • Experience with the A2A protocol, x402, or AP2 for agentic payments or agent-to-agent communication.
  • Experience with Kubernetes, Terraform, or equivalent tools for production-scale deployment.

About the Company

Santander

Global retail and commercial banking group

Santander is a global bank focusing on retail and commercial banking in Europe and the Americas, serving individuals and SMEs with regional franchises and a broad consumer finance arm, plus a Corporate & Investment Banking division for multinational clients. It uses its Gravity cloud platform to migrate core banking and rapidly deploy digital services such as Openbank across markets, combining fintech-style agility with a bank's balance sheet. The bank differentiates itself by marrying a large retail footprint with global CIB capabilities under the One Santander verticals model to boost efficiency and cross-border revenue. Its goals include improving returns on tangible equity and financing the green economy through sustainable finance and renewable energy projects.

Company size
10,001+
Company stage
IPO
Headquarters
Boadilla del Monte, Spain
Founded
1902

Recently Posted Jobs

Explore more opportunities at Santander

See more jobs