Hybrid Frontier Agentic AI Engineer - Production Systems

BlackCube Labs; España; Presencial; EUR 70.000 - 120.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Hybrid work model

Santander Open Academy access

Descripción de la vacante

Santander AI Lab (CDAIO) seeks a Frontier Agentic AI Engineer based in Madrid, Spain. The AI Lab builds production-grade agentic AI with multi-agent orchestration, memory, and tool-use, partnering with industry leaders to deliver real bank value.

You will design and deploy agentic systems, fine-tune LLMs for regulated banking use cases, and architect MCP servers and federated APIs, working in two-week sprints with researchers and data scientists.

Formación

• 4–8 years software or AI engineering experience, with ≥2 years building and maintaining LLM-powered systems in production environments.
• Demonstrated hands-on experience designing and deploying 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 (SFT, LoRA, RLHF) for domain-specific tasks, including dataset curation and evaluation design.
• Track record of delivering complete systems independently within tight timelines — from architecture decision to production-ready code.
• Experience building and consuming REST APIs and integrating AI systems with enterprise data sources, cloud services and third-party platforms.
• Prior experience in banking, fintech, or other regulated industries (Preferred).
• Exposure to Harness Engineering methodologies: spec-driven development, AI-assisted software creation at scale (Preferred).

Responsabilidades

• Designing, building and deploying production-grade agentic AI systems — multi-agent orchestration with real memory, planning, tool use and error recovery.
• Developing and fine-tuning small and medium language models (SLMs) for regulated banking use cases, including custom evaluation frameworks and domain-specific benchmarks.
• Architecting and implementing MCP servers, A2A protocols, and federated API layers that allow AI agents to operate across the group’s multi-country infrastructure.
• Prototyping new ideas in two-week sprints: hypothesis, architecture, code, functional demo, one-pager.
• Collaborating with researchers, data scientists and business stakeholders to translate complex technical concepts into tangible bank value.
• Keeping the lab at the frontier: monitoring emerging research, evaluating new tools, and integrating them into the lab’s workflow when they add real value.
• Producing clean, tested, observable code that can be handed off to the AI Science team for production scaling.

Conocimientos

Agentic AI systems

Multi-agent orchestration

SFT/LoRA/RLHF

REST APIs

Banking/fintech domain

Harness Engineering

Python

Agentic frameworks

LLM APIs

AWS cloud

FastAPI

Docker

Git / CI/CD

Kubernetes

MCP server

Terraform

GraphRAG

A2A protocol

Educación

Bachelor’s or Master’s in CS/SE/Math/Physics

Master’s in AI/ML or related field

Herramientas

LangGraph / AutoGen / CrewAI

Semantic Kernel

Anthropic Claude API/OpenAI

AWS Bedrock/Lambda/SageMaker/S3

FastAPI

Descripción del empleo

Santander AI Lab (CDAIO) seeks a Frontier Agentic AI Engineer based in Madrid, Spain. The AI Lab builds production-grade agentic AI with multi-agent orchestration, memory, and tool-use, partnering with industry leaders to deliver real bank value.

You will design and deploy agentic systems, fine-tune LLMs for regulated banking use cases, and architect MCP servers and federated APIs, working in two-week sprints with researchers and data scientists.