AI Engineer

About the Position

Turn large language models into real business systems. Build intelligent architectures that scale beyond experimentation.

Location: Santa Maria da Feira, Portugal [On location]

Employment Type: Full Time

Responsibilities

• Design, build, and productionize AI and GenAI solutions for enterprise use cases
• Develop and optimize LLM-based applications, including RAG pipelines and agentic or workflow-based systems
• Integrate LLM capabilities into existing applications, APIs, and enterprise platforms
• Design and implement evaluation strategies to measure the quality, reliability, and performance of LLM applications
• Build production-ready solutions with appropriate testing, monitoring, observability, and CI/CD practices
• Collaborate with technical teams, business stakeholders, and international clients to translate ambiguous requirements into robust technical solutions
• Contribute to technical design decisions, architecture discussions, and engineering best practices
• Share knowledge, mentor colleagues, and contribute to the continuous evolution of GenAI engineering practices

Requirements

• 5+ years of professional software engineering experience, with significant hands-on experience in AI/ML/GenAI
• Advanced proficiency in Python and commonly used libraries for data processing, machine learning, and AI development
• Hands-on experience implementing and deploying LLM-based solutions in production
• Experience designing and building RAG architectures with vector databases
• Experience building LLM workflows or agentic systems using an orchestration framework
• Strong software engineering fundamentals, including API development, testing, system design, CI/CD, and production observability
• Hands-on experience designing or implementing evaluation strategies for LLM applications (retrieval quality, groundedness, hallucination detection, regression testing)
• Fluent English, required for working with international clients

Nice to Have

• Experience with fine-tuning and model evaluation on cloud AI platforms
• Experience with AI quality, governance, and responsible AI practices
• Experience with model deployment in containers and MLOps practices
• Familiarity with more than one cloud ecosystem

Tech Skills

• Python & ML: Pandas, NumPy, Scikit-learn, PyTorch, TensorFlow
• LLMs: GPT-4, Claude, Llama 3, or equivalent models
• Vector Databases: ChromaDB, Pinecone, Weaviate, Milvus
• Orchestration Frameworks: LangChain, LlamaIndex, Haystack
• Cloud AI Platforms: IBM watsonx.ai, AWS Bedrock, Azure AI
• Evaluation Frameworks: Ragas, Giskard
• Containers & MLOps: Docker, Kubernetes
• Cloud Ecosystems: IBM Cloud, AWS, Azure

Soft Skills

• Enjoys technical knowledge sharing, mentoring, and continuous learning
• Strong analytical and problem-solving skills, with the ability to work effectively in ambiguous and evolving GenAI environments
• Comfortable communicating technical concepts to both technical and non-technical stakeholders

We Offer

• Competitive salary
• Opportunity to work in a dynamic and innovative environment
• Collaborative and inclusive company culture
• Professional development opportunities

About the Company

At Umain Works, we are dedicated to transforming businesses through cutting-edge AI technologies. Our team of experts is passionate about developing intelligent systems that drive real-world results. Join us in our mission to push the boundaries of what's possible with AI.