Artificial Intelligence Engineer

Migx
Barcelona, Spain
2 days ago

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Working hours
Regular working hours
Languages
English, Spanish, Catalan

Job location

Barcelona, Spain

Tech stack

API
Agile Methodologies
Artificial Intelligence
Amazon Web Services (AWS)
Azure
Continuous Integration
Data Security
Monitoring of Systems
Information Retrieval
Python
Scrum
Search Technologies
Systems Integration
Management of Software Versions
AI Infrastructure
Chatbots
Retrieval-Augmented Generation
Large Language Models
Prompt Engineering
Generative AI
Backend
FastAPI
Containerization
Machine Learning Operations
GPT
GXP
Docker

Job description

We're looking for an AI Engineer to join our Data and AI Engineering team. This role is ideal for those who are passionate about turning the latest AI advances - particularly LLMs (Large Language Models) - into production-ready tools, applications, and platforms.

You'll work on the front lines of applied AI, helping to develop intelligent systems, scalable infrastructure, and internal platforms that power the next generation of life sciences solutions.

Whether you're just getting started or bring years of hands-on experience, we welcome engineers who thrive in collaborative, exploratory, and engineering-focused environments.

Responsibilities

What You'll Do

  • Design, build, and deploy LLM-powered applications and internal tools for use cases such as document understanding, process automation, and knowledge retrieval.
  • Develop reusable AI infrastructure and platform components that support application teams (e.g., retrieval-augmented generation, prompt management, model orchestration).
  • Work with embeddings, vector stores, and similarity search to enable contextual AI responses.
  • Integrate with vector databases (e.g., FAISS, Weaviate, or Pinecone) to support semantic search and information retrieval.
  • Build scalable APIs and services using FastAPI or similar frameworks.
  • Use tools like MLflow to manage model experimentation, versioning, and deployment.
  • Collaborate closely with Data Engineers and Backend Engineers to ensure smooth data access, secure service delivery, and continuous integration.
  • Apply good engineering practices around testing, observability, and CI/CD for AI components.
  • Support discussions on AI ethics, responsible usage, and explainability - especially for regulated use cases.
  • Contribute to architectural decisions, product discussions, and agile ceremonies., * Hybrid work model and flexible working schedule that would suit night owls and early birds
  • 25 holiday days per year
  • Possibilities of career development and the opportunity to shape the company future
  • An employee-centric culture directly inspired by employee feedback - your voice is heard, and your perspective encouraged
  • Different training programs to support your personal and professional development
  • Work in a fast growing, international company
  • Friendly atmosphere and supportive Management team.

Requirements

  • Hands-on experience working with or deploying LLM-based systems (e.g., GPT, Claude, LLaMA, Mistral, etc.).
  • Proficiency in Python, with experience building services using FastAPI or similar frameworks.
  • Working with embeddings for text or document representation and semantic search.
  • Familiarity with vector databases (e.g., FAISS, Weaviate, Pinecone).
  • Understanding of AI infrastructure: versioning, tracking, and deployment with tools like MLflow.
  • Exposure to building production-grade APIs, services, or workflows in an agile, collaborative environment.
  • Awareness of AI ethics, responsible AI practices, and explainability concerns.
  • Team-first mindset and experience in agile environments (Scrum or Kanban).
  • Professional working proficiency in English (our internal and client-facing working language).

Requirements - Nice to have

Nice to Have

  • Experience with Docker and Kubernetes for containerization and orchestration.
  • Knowledge of prompt engineering, retrieval-augmented generation (RAG), or LangChain/LLamaIndex.
  • Experience with cloud-agnostic infrastructure or MLOps across Azure, AWS, or GCP.
  • Background in regulated industries (life sciences), especially GxP environments.
  • Familiarity with CI/CD pipelines and monitoring tools for AI workloads.
  • Experience integrating LLMs into real-world applications such as chatbots, document classifiers, or summarizers.
  • Spanish and/or Catalan language skills.

About the company

MIGx is a global consulting company with an exclusive focus on the healthcare and life science industries, with their particularly demanding requirements on quality and regulatory aspects. We have been managing challenges and solving problems for our clients in the areas of compliance, business processes and many others. MIGx interdisciplinary teams from Switzerland, Spain and Georgia have been taking care of projects in the fields of M&A, Integration, Application, Data Platforms, Processes, IT management, Digital transformation, Managed Services and compliance.

Apply for this position