Tensordyne

Working Student - ML Compiler

Munich, Germany
Level
Intern

Not stated in the posting: salary, work type, visa.

Open. First seen 27 October 2026.

Apply on the company's site →

About the role

On-site | Part-time (20 hours per week)

About Tensordyne

Tensordyne's standard text

Artificial intelligence (AI) is transforming our world. It can perform cognitive functions that previously only humans could do, such as perceiving interactions across different modalities and environments - with the ability to quickly learn and then solve complex problems. Tensordyne is an AI system solution company that builds very high-performance, low-power generative AI inference systems.

Our mission, through the creation of custom silicon, hardware and software, is to enable multimodal Generative AI inference acceleration at scale, with safe, sustainable, high-performance systems for our hyperscaler and neocloud data center customers. We are at the leading edge of advancing the latest research and product improvements for generative Al inference solutions that will make Al even more advantageous for compelling new generative AI applications.Tensordyne is a well funded, fast-paced startup company with headquarters in both Sunnyvale, CA, and Munich, Germany. We also have many talented team members working remotely across North America and Europe.

We take care of our people and their families with comprehensive benefits, competitive compensation, flexible spending options, and recognition programs, because building category-defining technology starts with a healthy, supported team. Come join us as we shape the future of multimodal generative artificial intelligence!

The Opportunity

At Tensordyne, we are at the forefront of cutting-edge AI hardware and software solutions. To keep pace in this dynamic, interdisciplinary field, we are seeking a Working Student in ML Compiler Engineering to contribute to the development of compilers for our custom ASICs.

This role offers an exciting opportunity to gain hands-on experience in full-stack compiler engineering while working alongside a team of experts in a fast-paced, innovative environment. If you are passionate about machine learning compilers, numerical programming, and performance optimization, we’d love to hear from you!

As a working student, you’ll gain valuable experience in a dynamic and innovative environment that thrives on curiosity and collaboration. This part-time role (20 hours per week) is based on-site at our Munich office..

The specific duties of this role will be shaped by both our business priorities and your individual interests.

Your Responsibilities

  • Design and implement ML compiler passes and optimizations tailored for our custom ASIC architecture.
  • Develop intuitive tooling to elevate the developer experience of our production ML compiler.
  • Work closely with multi-disciplinary teams, ranging from ML to embedded system engineers.

What you'll bring

  • A highly motivated, curious, and detail-oriented mindset with a strong desire to learn.
  • Passion for compilers
  • Solid understanding of graph theory and graph algorithms.
  • Proficiency in at least one systems programming language (e.g., C++, Rust).
  • Experience with Python and its ecosystem.
  • Currently enrolled in a Master's program in Electrical Engineering, Robotics, Computer Science, or a related AI field.

Nice to Have

  • Familiarity with parallel programming frameworks such as CUDA or OpenMP.
  • Interest in programming language design and compiler theory.
  • Experience with performance optimization.
Tensordyne's standard text

Tensordyne's culture was built on the following values:

  • Put people first. We only succeed when our people succeed.
  • Ethics and integrity always; Being open, honest, and respectful of everyone.
  • Think Big. Be ambitious and have audacious goals.
  • Aim for excellence. Quality and excellence count in everything we do.
  • Own it and get it done. Results matter!
  • Make each person better together, than they would be as an individual.
  • Embrace each others’ differences, and embrace that there will be differences.

Tensordyne is an equal opportunity employer. We believe that a diverse team is better at tackling complex problems and coming up with innovative solutions. All qualified applicants will receive consideration for employment without regard to age, color, gender identity or expression, marital status, national origin, disability, protected veteran status, race, religion, pregnancy, sexual orientation, or any other characteristic protected by applicable laws, regulations and ordinances.

A note to Recruitment Agencies: Please don’t reach out to Tensordyne employees or leaders about our roles -- we’ve got it covered. We don’t accept unsolicited agency resumes and we are not responsible for any fees related to unsolicited resumes. Thank you for your understanding.

What this role asks for

Particular to this role

CUDA · Embedded Systems

Rare in Tensordyne's other 20 open postings.

Standard for data science / ML roles

Machine Learning · Python

Common in data science / ML postings at any company.

In most of Tensordyne's ads

Generative AI

Named in most of its open postings, whatever the role.

63% of this description is written for the role. The rest is Tensordyne's standard text, folded away below.

Compared with Tensordyne's other open jobs.

The team: Engineering HIRES STEADILY

This role is one of 20 open in Engineering. 5 were posted in the last 30 days and the oldest in April: a team that hires all year rather than one being built.

WHAT THE TEAM WORKS WITH, ACROSS ITS POSTINGS

Generative AI (20 of 20), C++ (9 of 20), Python (9 of 20), Rust (6 of 20), C (5 of 20), Verilog (5 of 20), Embedded Systems (3 of 20)

OTHER ROLES ON THIS TEAM

From the team and dates on Tensordyne's own job board.

Similar jobs

More jobs like this

SKILLSPython 46,059Machine Learning 19,797C++ 11,892Generative AI 8,208AI and machine learning 8,842
PLACESMunich 846Germany 3,224
COMPANYJobs at Tensordyne 22

Is this your posting? Email info@careerholo.com to have it removed.