• You will conduct comprehensive literature reviews and State-of-the-Art (SoTA) analyses of current research on LLM context engineering, repository-scale retrieval-augmented generation (RAG), and agentic workflows for software development.
  • As part of setting up and maintaining agent infrastructure, you will configure and manage execution sandboxes, agent harnesses, and test environments.
  • To assess real-world impact, you will implement and run benchmarks on repository-level coding use cases, measuring performance, output accuracy, and developer productivity gains.
  • Furthermore, you will propose, prototype, and evaluate generic context pipelines for AI coding agents.
  • Finally, you will document scientific methodologies and findings and present your results to the research team.

 

We are looking for a Brussels-based intern, with a background in European studies, politics, international affairs or other social science fields and an interest or experience in our field of expertise. The intern will work closely with the Participatory Strategy team and be strongly involved in our ongoing projects. This will involve in particular:

  • Contribute to the project development of future potential opportunities;
  • Support our general project implementation, organisation and management;
  • Drafting policy notes, publications and posts for social media;
  • Network and partnership management (incl. NGOs, public partners & foundations);
  • Reporting back from relevant conferences and events, such as informal meetings.
  • Support the organisation and implementation of events.
  • Support the delivery of new consumer experiences from journey design, specification, mapping & implementation starting with the identification of first party data flowing into Mazda CRM systems
  • Help enrich and maintain our 360° customer view, bringing together insights from multiple touchpoints to better understand our customers and their needs
  • By supporting data quality initiatives, you will ensure that our teams can rely on accurate, high-quality information to make smarter decisions and deliver impactful campaigns
  • Provide reporting and presentations on project progress, problems, and solutions to Consumer Intelligence Manager/Team Lead
  • Collaborate with an international team who are passionate about innovation and customer experience
  • Organise and support regular project meetings with cross-functional team at Mazda Europe as well as European markets
  • Monitor KPI framework
  • Support the daily operations for Mazda’s European CRM platform
  • Create newsletters for all European markets around CRM Development and Consumer Intelligence Platform highlights
  • Engage with the team on CRM Platform Roadmap as well as the Consumer Intelligence Vision & Strategy
  • Providing critical feedback based on latest methodologies on CRM in general and tool specific observations if possible.
  • You will support the Climate team in the analysis and improvement of the methodology for calculating the scope 3 carbon footprint (non-FLAG and FLAG).
  • You will contribute to the integration and modeling of CO2 initiatives deployed at the group level.
  • You will support the implementation and monitoring of subsidiary CO2 action plans to achieve the 2030 CO2 ambition.
  • You will support other related projects: guidelines, external collaboration, legislation and standards, benchmarks, ...
  • You will contribute to the annual Extra-Financial reporting exercise on the Climate part.
  • Build a productized replay "run command" — a single, parameterized entry point that resolves automatically and without the need of expert knowledge to launch a run.
  • Develop a direct bug-replay workflow that reproduces a reported issue straight from its recording and proves that an implemented fix is working as expected.
  • Implement replay tests for the CI so it triggers on every new build drop and returns a clear pass/fail verdict, protecting releases from silent regressions.
  • Work hands-on with large-scale recorded sensor data and a production autonomous-driving stack.
  • Deliver foundational infrastructure that makes autonomous-driving software faster and safer to ship across NVIDIA's automotive customers.
  • Support with vehicle and feature testing as needed onsite in Munich.