AI Engineer (f/m/x)

HEY THERE!

We are Mercedes-Benz.io. Our mission is to ignite and build digital solutions for Mercedes-Benz by bringing together a tribe of digital enthusiasts who drive the digital future of mobility.

We believe flexibility and collaboration go hand in hand. With offices in Lisbon and Braga, we offer a flexible hybrid setup, with an average of one day per week in the office. This allows for meaningful in-person collaboration while maintaining the flexibility to work in a way that best supports you and your team.

We do not care about your shoes, as long as you bring the right attitude. At Mercedes-Benz.io we walk the talk and make things happen. We do not digitise for the sake of being digital, but to create real value. We reflect, challenge the status quo, and stand up for each other. This is why we hire people who want to make an impact.

ABOUT THE ROLE

As an AI Engineer, you will help shape the next generation of AI-powered products and experiences at Mercedes-Benz.io. Working at the intersection of software engineering and AI, you will design, build, and scale intelligent solutions that solve real business challenges and deliver measurable impact. Collaborating with product teams, software engineers, and domain experts, you will develop and operate production-ready AI systems that transform AI capabilities into reliable and scalable outcomes.

IN THIS ROLE YOU WILL

-

Analyze and decompose complex problems, determining where AI-driven reasoning adds value and where deterministic, testable software is the better solution.

-

Evaluate and select models, frameworks, and technologies, balancing quality, latency, scalability, cost, and production readiness.

-

Design, build, and operate AI systems and agentic solutions, including single-agent and multi-agent architectures, applying sound engineering judgment when deciding where agentic approaches add value.

-

Develop AI-powered applications using LLMs, prompts, structured outputs, tool-calling capabilities, and orchestration logic, treating these components as production-grade software.

-

Build retrieval and knowledge systems, including retrieval pipelines, embeddings, chunking strategies, grounding mechanisms, and context management approaches that improve response quality and reliability.

-

Implement Responsible AI practices, including guardrails, privacy protections, security controls, auditability, human oversight, and regulatory compliance.

-

Define and execute evaluation strategies through test datasets, quality assessments, performance measurement, regression testing, and failure analysis to ensure reliable AI behaviour over time.

-

Ensure production reliability and observability through monitoring, tracing, logging, metrics, performance management, and operational readiness practices.

-

Investigate and resolve AI system failures, identifying root causes across retrieval, prompting, context management, model behaviour, planning, and tool usage while designing recovery and fallback mechanisms that improve system resilience.

-

Contribute to shared AI platforms and engineering practices by building reusable components, promoting standards, and sharing knowledge across the engineering community.

-

Act as an advocate for AI engineering excellence, helping grow AI capabilities across teams through knowledge sharing, best practices, and technical enablement.

-

Collaborate closely with stakeholders and domain experts to define requirements, validate outcomes, communicate limitations, and foster appropriate trust in AI-powered solutions.