SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Tensordyne is an AI infrastructure company building high-performance, low-power generative AI inference systems through custom silicon, hardware, and software. The company serves hyperscaler and neocloud data center customers with multimodal AI inference acceleration solutions.
You will join as a Simulation & Modeling Engineer, working on the functional model of Tensordyne's inference accelerator. This is a hands-on role bridging software and hardware engineering—you'll write maintainable code, understand hardware deeply, and tackle complex modeling challenges.
Key responsibilities:
- Implement new architecture features and algorithms in the simulation model
- Investigate discrepancies between model behavior and hardware behavior
- Write comprehensive tests, test plans, and test infrastructure; track code coverage
- Document the model and validate it against architecture specifications and RTL (Register Transfer Language)
- Evaluate and adopt new modeling techniques to improve the codebase
- Maintain and enhance the modeling codebase
- Collaborate closely with architecture, hardware, and software teams
You'll work in a well-funded, fast-paced startup with headquarters in Sunnyvale, CA and Munich, Germany, plus remote team members across North America and Europe.
Requirements:
- Strong modern C++ programming skills
- Good knowledge of RTL and ASIC methodology
- Solid understanding of hardware architecture
- Proficiency with build systems and toolchains
- Ability to take loosely specified features and deliver working, tested code with minimal guidance
- Clear written and verbal communication; comfort working across teams
- BS or higher in Computer Science, Computer Engineering, Electrical Engineering, or related field
- 3+ years of industry experience
Nice to have:
- SystemC / TLM-2.0 knowledge
- Experience with AI/ML accelerators or GPU architectures
- High-performance computing background
- Python for scripting and tooling
- Proficiency with debugging and analysis tools (sanitizers, profilers, tracing)
