Apertus Engineer: Deployment

Join Our Innovative Engineering Team

We are on the lookout for a talented engineer passionate about shaping the technical landscape of advanced AI models. This role involves integrating our cutting-edge Apertus models into the open-source inference ecosystem, ensuring seamless functionality for the community, and producing quantized variants to enhance deployment versatility.

Key Responsibilities

• Upstream Integration and Release Engineering:
  • Lead the technical release path for Apertus models, collaborating with the training team on checkpoint conversion and preparing release artifacts.
  • Implement and support Apertus model architectures within prominent community libraries, guiding contributions through the review process.
  • Ensure compatibility of new releases with major inference engines and model formats from day one.
  • Coordinate with the community manager on release timing and required technical materials.
• Quantisation:
  • Create quantized model variants suitable for both server and personal deployment, maintaining quality through rigorous evaluation benchmarks.
• Documentation and Examples:
  • Provide exemplary scripts and reference configurations for using Apertus models, supporting various ecosystems.
  • Maintain clear deployment documentation and troubleshooting guides for community users.

Essential Qualifications

• MSc or PhD in Computer Science, Data Science, Artificial Intelligence, Machine Learning, or related fields. Exceptional BSc candidates with strong engineering experience are also welcome.
• Proficient in Python, with a solid foundation in software engineering and open-source contribution workflows.
• Experience with LLM inference stacks and strong collaboration and communication skills.
• A high degree of flexibility in adapting to dynamic priorities and schedules.
• A demonstrated history of merged contributions to ML or inference libraries.

Preferred Skills

• Experience converting models between various formats and frameworks.
• Familiarity with personal deployment tools and strong documentation skills.

Additional Attributes

• Engage in a stimulating academic environment at a prestigious technical university.
• Access to state-of-the-art supercomputing resources.
• Collaborate with leading researchers and engineers in the field.
• Enjoy attractive employment conditions with comprehensive benefits.
• Flexible working arrangements, including options for remote work, are available.
• Professional development opportunities such as conference attendance and specialized training.
• Contribute to impactful open-source projects and participate in Switzerland's sovereign AI development.

This role is based in either Lausanne at EPFL or Zürich at ETH Zürich. We look forward to welcoming a dedicated professional eager to make a significant impact in the field of AI and open source.