Skip to main content
T

Jr Software Engineer - ML Runtime - Rust

Tensordyne
August 27, 2026
Full-time
On-site
Munich, BY, Germany
Other Semiconductor Jobs, Level - Entry or Early Career

Job Title

Jr Software Engineer - ML Runtime - Rust

Role Summary

Join the Low-Level Runtime team to implement and maintain a high-performance ML model execution framework in Rust, targeted to run on Tensordyne custom hardware. Work includes porting model components to the runtime, optimizing model performance and utilization, and debugging in both virtual and physical hardware environments.

Experience Level

Entry-level (Junior). Typically suitable for candidates with approximately 0–3 years of relevant experience.

Responsibilities

Primary responsibilities focus on development, optimization, and productization of ML runtime components and models for Tensordyne hardware.

  • Develop and maintain low-level ML model execution framework in Rust.
  • Port and maintain model components to run on the company’s hardware and runtime.
  • Optimize performance and hardware utilization of ML models.
  • Debug and productize models in virtualized and physical hardware environments.
  • Collaborate with cross-functional teams to integrate models and validate performance.

Requirements

Technical skills and experience expected for successful performance in this role.

Must-have

  • Experience with the Rust programming language.
  • Familiarity with high-level ML model concepts such as LLMs and attention architectures.
  • Experience with low-level code development (for example, embedded systems or similar).

Nice-to-have

  • Experience building LLM engineering workflows and driving agents.
  • Experience with Google Cloud Platform or similar cloud providers.
  • Experience with Python for tooling, testing, or model integration.
  • Deep knowledge of modern LLM attention architectures (e.g., GDN, DSA, KDA).

Education Requirements

Not specified.


About the Company

Company: Tensordyne

Tensordyne is a startup developing high-performance, low-power AI inference processors and multi-chip systems for generative AI acceleration in data centers. The company focuses on ASIC design, verification, and integration of computational accelerators with third-party SoC IP.

Tensordyne logo

Date Posted: 2026-08-26