AI Engineer Leiria

AI Engineer
Leiria
Leiria, Leiria District, Portugal

About Us

At xgeeks, we are on a mission to accelerate success with AI and Cloud-Native development Making the promise of Dev
Ops, Data, and Digital Solutions impact a reality.

Here, you’ll be able to design and implement AI and Cloud-Native solutions for
- ups,
- ups, and some of the biggest companies in Europe, alongside an international, multidisciplinary team, all from our offices in Leiria, Lisbon and Viseu (so far!)!

As part of the synvert Group, you’ll be joining a global network of
- tier technology experts with the ability to push your creative boundaries while tapping into the expertise and resources of a larger, international tech powerhouse. Together, we’re expanding our impact and delivering even stronger solutions for our clients.

Our Tech Stack

We consider a good software engineer to be someone who can quickly pick up any technology, and more importantly, knows the right tool for the job.

Curious about our stack? Here’s a glimpse:

Skills And Qualifications

We’re looking for a
- on AI Engineer to join our team and help transform frontier AI capabilities, particularly LLM-powered agents and
- agent systems, into impactful
- world solutions.

In this role, you’ll collaborate closely with engineering, product, and client teams to design and deliver
- grade AI features. This includes crafting effective prompt strategies and sophisticated agent flows, implementing Retrieval-Augmented Generation (RAG) pipelines for robust knowledge access, and applying AI to data analysis workflows. You will focus on applying the right tools to the right problems, ensuring our solutions are valuable, reliable, maintainable, predictable, and adhere to strict compliance and security standards through rigorous evaluation and observability practices.

Key Responsibilities

• Integrate and deploy LLM APIs and Models (e. g. , Open
  AI, Claude, Mistral, Hugging Face) into applications, internal tools, and backend workflows.
• Design and iterate on prompt strategies and agent flows for use cases like customer support, developer tools, data validation, and operational automation.
• Build and maintain AI workflows using orchestration libraries and frameworks (e. g. , Open
  AI Agents SDK, Lang
  Chain, Lang
  Graph, Lite
  LLM, RAG pipelines).
• Contribute to the development and optimisation of infrastructure for embedding generation, vector search, and metadata enrichment (e. g. , Pinecone, pgvector, Chroma, Cloudflare Vectorize, or Qdrant)
• Ensure AI-powered systems are testable, observable, performant, and aligned with compliance and security standards. (e. g. designing and implementing evals, Open
  Telemetry standard)
• Stay
  -
  - date with developments in Gen
  AI, ML engineering, and MLOps, and actively assess new tools and techniques.
• Contribute to a culture of experimentation, continuous improvement, and
  - focused engineering.
  
  

• 2+ years of
  - on experience in backend software engineering or ML engineering, preferably with a focus on AI applications and agent development
• Proficient in Python or Node. js, with experience in building robust and maintainable systems.
• Hands-on experience integrating LLM APIs and/or building ML pipelines in
  - world production applications.
• Solid understanding of prompt engineering, agentic design patterns, and
  - augmented generation.
• Familiarity with AI/ML libraries or platforms such as Lang
  Chain, Transformers,
  - learn, or equivalent.
• Experience with CI/CD workflows, Docker, and cloud services (preferably AWS or Azure).
• Strong
  - solving skills and a pragmatic,
  - oriented mindset.
• Fluent in English with strong communication and collaboration skills.
  
  

• Exposure to agentic architectures or orchestration tools (e. g. , Lang
  Graph, Airflow, Temporal).
• Familiarity with vector databases (e. g. , Pinecone, Qdrant, Weaviate, pgvector) or semantic search tools.
• Experience working on data science projects or building ML models beyond LLM use cases.
• Strong understanding and practical application of evaluation strategies and observability for AI systems