As an AI Engineer specializing in Generative AI, your role is crucial in turning AI capabilities into reliable, production-ready products. You will design, build, and maintain the services, agents, and retrieval pipelines that power our AI solutions, ensuring they are robust, scalable, and optimized for performance and cost. By combining large language models, modern APIs, and sound software engineering, you will drive innovation and enhance our AI capabilities.

Your expertise in AI and backend development will enable you to integrate models into existing systems, expose them as secure and efficient APIs, and collaborate with multidisciplinary teams to deliver features end to end. Your work will directly impact our ability to automate processes, extract structure from documents and text, and deliver AI features our customers rely on.

RESULTS & RESPONSIBILITIES

- Design, build, and maintain AI services and APIs that are robust, secure, and ready for production.
- Develop AI agent-based and multi-agent solutions, integrating them with language models, tools, and modern APIs.
- Develop intelligent document processing solutions using Generative AI to classify documents and extract metadata, transforming unstructured data into structured formats.
- Design and implement Retrieval-Augmented Generation (RAG) pipelines, including document ingestion, chunking, embeddings, vector indexing, and semantic search.
- Build data pipelines that prepare and process unstructured data for AI systems.
- Implement automated evaluation and testing of AI features, so that changes to prompts, models, or retrieval can be validated before release.
- Collaborate with backend, DevOps, and product teams to integrate AI features into existing systems, with attention to scalability, maintainability, and cost.
- Containerize and deploy AI services to the cloud and contribute to their CI/CD pipelines.
- Evaluate and select open-source and commercial models for specific use cases, balancing quality, latency, and cost.




- Design and experiment with novel prompting strategies and few-shot learning techniques to optimize model outputs.
- Optimize inference performance, latency, and cost through techniques such as caching, batching, and model selection.
- Prototype and validate experimental AI features in a controlled sandbox before production deployment.
- Monitor AI services in production, tracking quality, latency, errors, and cost, and act on issues as they arise.
- Apply data privacy and data governance practices when working with supplier and customer data.

PERSON SPECIFICATION

Competencies

DECISION MAKING

- Identify, evaluate and potentially present options for implementation of solutions.
- Articulate and document the assumptions and any risks involved in options.
- Involve appropriate stakeholders in drawing conclusions, while being able to make decisions independently and effectively.
- Communicate decisions clearly to those who are affected.

CUSTOMER FOCUS
- Have a clear understanding of the internal and external customers and their requirements.
- Work collaboratively with Product Owners to establish expectations, needs and agree deliverables required.
- Strive to deliver a high quality, maintainable product matching quality and expectations.

MANAGING CHANGE
- Respond constructively and effectively to changing requirements that may affect sprint goals or deliverables.
- Manage time and priorities to ensure work is delivered on time.
- Impact assess any changes on existing solution, requirements and timelines for delivery.
- Ensure any risks to delivery are communicated to management in a timely manner.

KNOWLEDGE





- Working knowledge of Scrum, Nexus and other Agile practices. Knowledge of Test Driven Development, Gherkin is desirable as well.

EXPERIENCE

Experience in the following is essential:

- At least 5 years of experience in software or AI engineering, including at least 2 years building AI or machine learning solutions.
- Strong experience as a Python developer, applying best practices in software development, testing, and code review.
- Experience building REST APIs and microservices with frameworks such as FastAPI.
- Practical experience implementing AI agents and multi-agent architectures with frameworks such as LangGraph or LangChain.
- Real-world experience with Generative AI and large language models in production projects.
- Real-world experience with RAG systems and vector databases such as Qdrant, FAISS, or Azure AI Search.
- Experience with the Azure ecosystem and its associated services for AI, such as Azure OpenAI.
- Working knowledge of SQL, Docker, Git, and CI/CD pipelines.
- Ability to process and transform large volumes of unstructured data, especially text (NLP, embeddings).
- Experience in prompt optimization for AI and designing Prompt Engineering strategies.
- Experience evaluating LLM outputs with custom metrics and automated tests.

Experience in the following is desirable:
- Experience with Kubernetes and pipeline orchestration tools such as Airflow.
- Experience with machine learning frameworks such as PyTorch or Hugging Face Transformers, including fine-tuning.
- Experience with LLM observability tools such as Langfuse or LangSmith.
- Experience with Azure Machine Learning, Azure Container Apps, or Azure Functions.

QUALIFICATIONS

- Degree in computer science, software engineering or equivalent work-based experience.
- Examples of own portfolio or source code are welcome.
- Professional working proficiency in English (B2 or higher), spoken and written.
- Fluent Spanish.

📌 AI Engineer with Specialization in Generative AI (Madrid)
🏢 Achilles Group
📍 Madrid