As our TT-Distributed Software Engineer, you will develop and optimize distributed software systems that power the most efficient and highest-performing AI and HPC clusters. In this role, you'll work on distributed programming across multiple nodes, utilizing systems programming, inter-node communication, and Tenstorrent's scalable architectures to advance the state-of-the-art distributed inference and training infrastructure.
This role ishybrid, based out of Santa Clara, CA; Austin, TX; or Toronto, ON.
We welcome candidates at various experience levels for this role. During the interview process, candidates will be assessed for the appropriate level, and offers will align with that level, which may differ from the one in this posting.
Who You Are- A strong C++ or systems software engineer with a solid foundation in compiler design, programming languages, or performance-oriented systems programming.
- Interested in compiler optimizations, computation graphs, parallel execution, and mapping workloads onto heterogeneous or distributed hardware.
- Comfortable reasoning about data movement, communication overhead, synchronization, and performance tradeoffs across multiple compute devices and nodes.
- Experienced in or eager to work with distributed execution, parallel programming models, and large-scale AI workloads.
- A first-principles problem solver who enjoys profiling complex systems, identifying bottlenecks, and translating performance insights into software optimizations.
What We Need- Design, implement, and optimize compiler and systems software that enables AI workloads to execute efficiently across multiple accelerators and compute nodes.
- Develop techniques for workload partitioning, graph transformation, scheduling, and parallel execution across distributed hardware.
- Optimize communication and computation together, including collective operations, synchronization, data movement, and communication-aware execution strategies.
- Build and improve distributed programming abstractions and runtime interfaces that connect compiler-generated execution plans with underlying hardware and communication infrastructure.
- Profile, benchmark, and debug distributed workloads to identify performance bottlenecks, validate optimizations, and collaborate with compiler, runtime, architecture, and AI software teams.
What You Will Learn- How compiler technology and distributed systems come together to scale AI inference and training across large accelerator clusters.
- Techniques for graph partitioning, parallelization, scheduling, and communication-aware compiler optimization.
- How compiler decisions affect data movement, network utilization, synchronization, and end-to-end workload performance.
- How Tenstorrent's hardware architecture, compiler stack, and distributed runtime interact to execute large-scale AI workloads.
- How to optimize end-to-end AI execution across the software and hardware stack, from computation graphs to multi-node accelerator clusters.
Compensation for all engineers at Tenstorrent ranges from $100k - $500k including base and variable compensation targets. Experience, skills, education, background and location all impact the actual offer made.
Tenstorrent offers a highly competitive compensation package and benefits
