Hiring Timelines

This internship opportunity is available throughout our 3 terms with the following corresponding recruitment cycles:

• Winter Term: Mar–May work term, Nov–Jan recruit.
• Summer Term: Aug–Oct work term, Jan–May recruit.
• Fall Term: Oct–Dec work term, Apr–May recruit.

Please note these timelines are for reference only. Actual timelines may vary.

At Tenstorrent, we believe the future of computing must be open, which is why our interns don’t just watch from the sidelines - they help build the core of it. We provide a "code-to-career" pipeline where students collaborate with industry experts to solve high-stakes problems in RISC-V and AI hardware-software co-design. By joining us, you are taking an internship to democratize high-performance computers that are accessible to everyone.

As an intern at Tenstorrent, you will experience working on a carefully defined and real engineering project, guided by a dedicated mentor and a manager, and as a part of a team. This role focuses on model training pipelines on the Tenstorrent compiler stack and how neural networks are brought up and optimized on our hardware. We are looking for a minimum of 3 months for this role with the potential for extension to 6 months. 

This role is on-site based in Belgrade, Serbia.

Who You Are

• Possessing or currently pursuing a Bachelor's or Master's degree in Computer Science, Electrical Engineering, or a related field.
• Strong understanding of neural network fundamentals.
• Proficiency in Python; experience with C++ is a plus.
• Ability to learn and work effectively within a team environment.

What We Need

• Participate in the implementation and validation of model training pipelines on Tenstorrent compiler stack, specifically using PyTorch and JAX.
• Support benchmarking, analysis, and performance optimization of various model architectures.
• Contribute to efforts in scaling out distributed model training under guidance and participate in discussions related to the co-design of Tenstorrent's hardware and software stack.
• Assist in the integration of Tenstorrent software with widely used tools in the machine learning community.

What You Will Learn

• The process of getting neural network models to train correctly and efficiently on our hardware.
• Techniques for benchmarking, analysis, and performance optimization of various model architectures.
• How to scale out distributed model training and participate in hardware–software co-design discussions.
• How Tenstorrent software integrates with widely used tools in the machine learning community and how a cross‑functional engineering team collaborates on real projects.

Hiring Timelines

This internship opportunity is available throughout our 3 terms with the following corresponding recruitment cycles:

• Winter Term: Mar–May work term, Nov–Jan recruit.
• Summer Term: Aug–Oct work term, Jan–May recruit.
• Fall Term: Oct–Dec work term, Apr–May recruit.

Please note these timelines are for reference only. Actual timelines may vary.

Tenstorrent offers a highly competitive compensation package and benefits, and we are an equal opportunity employer.

• Final-year BSc or MSc student in Computer Science, Software Engineering, Electrical Engineering, or a related technical field
• Strong programming fundamentals in Python, with familiarity in C++ considered a plus
• Interested in backend systems, API design, and how ML models are deployed in production environments
• Curious about performance optimization techniques such as batching, caching, and model parallelism
• Motivated to learn and contribute in a collaborative engineering environment

• Contribute to backend features and APIs that support AI inference workloads
• Assist in deploying, testing, and benchmarking models running on Tenstorrent hardware
• Analyze inference performance and help identify optimization opportunities
• Write clean, maintainable code with guidance from senior engineers
• Collaborate with the team to improve reliability, usability, and performance of the inference server stack

• How end-to-end ML inference is optimized on custom AI hardware
• How scalable backend systems are designed to serve real-world AI applications
• How APIs and infrastructure shape the developer experience for AI workloads
• Practical performance analysis techniques in production-like environments
• How modern AI software stacks integrate models, runtimes, and hardware

Hiring Timelines

This internship opportunity is available throughout our 3 terms with the following corresponding recruitment cycles:

• Winter Term: Mar–May work term, Nov–Jan recruit.
• Summer Term: Aug–Oct work term, Jan–May recruit.
• Fall Term: Oct–Dec work term, Apr–May recruit.

Please note these timelines are for reference only. Actual timelines may vary.

At Tenstorrent, we believe the future of computing must be open, which is why our interns don’t just watch from the sidelines - they help build the core of it. We provide a "code-to-career" pipeline where students collaborate with industry experts to solve high-stakes problems in RISC-V and AI hardware-software co-design. By joining us, you are taking an internship to democratize high-performance computers that are accessible to everyone.

As an intern, you will experience how we do engineering for 3-6 months, working on a carefully defined and real engineering project, guided by a dedicated mentor and a manager, and as a part of a team.

This role is on-site, based in our Belgrade office.

• You are a final-year BSc student or higher in Computer Science, Engineering, Math, or a related technical field.
• You have a strong passion for programming and a solid grasp of algorithms and data structures.
• You are proficient in programming languages, particularly Python and C++.
• You are passionate about neural networks and related deep-learning architectures.

• Design and implement Python/C++ APIs in our SDK for AI/ML developers.
• Extend the model-import pipeline to support new operators, tensor shapes, and graph patterns.
• Develop compiler passes (e.g., rewriting, tiling, optimization) using an MLIR-based infrastructure.
• Design logic for scheduling and executing compiled neural networks efficiently on our custom AI hardware.

• Gain practical experience in ML compiler development and MLIR infrastructure.
• Master high-performance programming in C++ and professional API design in Python.
• Understand hardware-software co-design principles for low-latency AI execution.
• Develop tools for performance analysis and visualization (e.g., hardware utilization, power consumption).

Hiring Timelines

This internship opportunity is available throughout our 3 terms with the following corresponding recruitment cycles:

• Winter Term: Mar–May work term, Nov–Jan recruit.
• Summer Term: Aug–Oct work term, Jan–May recruit.
• Fall Term: Oct–Dec work term, Apr–May recruit.

Please note these timelines are for reference only. Actual timelines may vary.

Tenstorrent offers a highly competitive compensation package and benefits, and we are an equal opportunity employer.

At Tenstorrent, we believe the future of computing must be open, which is why our interns don’t just watch from the sidelines - they help build the core of it. We provide a "code-to-career" pipeline where students collaborate with industry experts to solve high-stakes problems in RISC-V and AI hardware-software co-design. By joining us, you are taking an internship to democratize high-performance computers that are accessible to everyone.

As an Intern on our AI Performance & Debugging Tools and Low Level Kernels teams, you will help build the software that reveals how our AI processors behave and how modern neural networks execute on our systems. You will work on runtimes, kernels, and tooling that ship with Tenstorrent hardware so customers can deploy real AI workloads with confidence. We are looking for a minimum of 3 months for this role with the potential for extension to 6 months.

This role is onsite, based in our Belgrade, Serbia office.

Who You Are

• Currently pursuing a Bachelor’s or Master’s degree in Computer Engineering, Computer Science, or a related field.
• Proficiency in C++ or experience with system-level programming.
• Familiarity with Linux-based environments, including shell scripting and debugging tools.
• Basic understanding of computer hardware architecture and system-level programming.
• Interest in performance profiling, debugging, and AI-related workloads.

What We Need

• Build and optimize neural network execution and data movement in C, C++, and Python on our AI/ML chips, focusing on speed, efficiency, and low power.
• Develop and extend our SDK and tools in C++ and Python to provide clear APIs and simple views into performance, hardware use, placement, routing, and power.
• Build and improve developer tools for debugging, performance monitoring, and understanding system behavior, using feedback from engineers and developers.
• Work with hardware and compiler teams to tune system performance while learning low-level programming, and support testing, documentation, and other parts of the software lifecycle.

What You Will Learn

• How state-of-the-art neural networks are mapped, scheduled, and optimized on custom AI accelerators.
• How to design and tune low-level kernels and runtime firmware that directly drive AI-specialized engines and RISC-V cores.
• How to build and extend performance, profiling, and debugging tools used by AI and compiler engineers.
• How to work in Linux-based, system-level environments using C++, Python, shell scripting, and hardware debug tools.
• How to incorporate user and developer feedback into next iterations of performance and debugging tooling.

Hiring Timelines

This internship opportunity is available throughout our 3 terms with the following corresponding recruitment cycles:

• Winter Term: Mar–May work term, Nov–Jan recruit.
• Summer Term: Aug–Sep work term, Jan–May recruit.
• Fall Term: Oct–Dec work term, Apr–May recruit.

Please note these timelines are for reference only. Actual timelines may vary.

Tenstorrent offers a highly competitive compensation package and benefits, and we are an equal opportunity employer.

At Tenstorrent, we believe the future of computing must be open, which is why our interns don’t just watch from the sidelines - they help build the core of it. We provide a "code-to-career" pipeline where students collaborate with industry experts to solve high-stakes problems in RISC-V and AI hardware-software co-design. By joining us, you are taking an internship to democratize high-performance computers that are accessible to everyone. During this internship, you will bridge the gap between academic theory and industry practice  

This role is on-site, full time, based in Belgrade, Serbia.

Who You Are

• You are in your final year of undergraduate study, a recent graduate, or currently pursuing a master's degree in Computer Science or Electronics Engineering. 
• You enjoy tackling complex technical problems and naturally approach them with structured, analytical thinking. 
• You have written hardware in Verilog or VHDL and understand how HDL translates to physical logic. 
• You are genuinely curious about how processors and computer architectures work, not just in theory but at the implementation level. 
• You are comfortable working in C/C++ and can get things done with scripting languages such as Python, Perl, or Tcl. 
• Nice to have: experience in advanced digital hardware and system architecture (e.g., high‑frequency logic, processors/GPUs, SoCs and memory systems, real‑time hardware/firmware) and modern machine learning, including deep learning frameworks and models.

What We Need

• Architecture exploration and modeling.
• Implementation of Tenstorrent IP and SOC RTL logic in Verilog.
• Verification of Tenstorrent's IP and SOC logic using advanced verification methodologies.
• Low-level software development for hardware testing.

What You Will Learn

• Exposure to the complete RTL-to-GDSII flow. 
• Front-End Design & Logic Synthesis: Mastering Verilog/SystemVerilog to translate architectural specs into optimized hardware descriptions.
• Verification Methodologies: Developing robust testbenches and utilizing UVM (Universal Verification Methodology) and/or CocoTb to ensure "bug-free" silicon.
• Performance benchmark and optimizations
• Timing & Power Analysis: Performing Static Timing Analysis (STA) and power optimization to meet aggressive performance targets.
• Sign-off & Tape-out Readiness: Understanding the rigorous checks required to prepare a design for fabrication.

Hiring Timelines

This internship opportunity is available throughout our 2 terms with the following corresponding recruitment cycles:

• Summer/Fall Term: Aug-Jan work term, Apr–May recruit.
• Winter/Spring Term: Jan–June work term, Nov–Dec recruit.

Please note these timelines are for reference only. Actual timelines may vary.

Tenstorrent offers a highly competitive compensation package and benefits, and we are an equal opportunity employer.

At Tenstorrent, we believe the future of computing must be open, which is why our interns don’t just watch from the sidelines - they help build the core of it. We provide a "code-to-career" pipeline where students collaborate with industry experts to solve high-stakes problems in RISC-V and AI hardware-software co-design. By joining us, you are taking an internship to democratize high-performance computers that are accessible to everyone.

During your internship, you will partner with highly skilled engineers, experience many approaches to problem‑solving, and work on a carefully defined engineering project in relation to convolutions and their optimizations for Tenstorrent hardware, guided by a dedicated mentor. We are looking for a minimum of 3 months for this role with the potential for extension to 6 months.

This role is onsite, based in our Belgrade office.

Who You Are

• Enrolled in the final year of BSc or MSc studies in Computer Science, Computer Engineering, Software Engineering, Electronics, Math, or a related field.
• Comfortable with one or more programming languages, including C++ and Python.
• You bring a solid foundation in algorithms and data structures and basic familiarity with machine learning frameworks and concepts.
• You are curious about kernel development, low‑level and tensor optimizations, and performance profiling, and want to deepen your skills in these areas.

What We Need

• Contribute to the design, development, and maintenance of Tenstorrent software components connected to our hardware platform, and implement and optimize kernels for convolution‑based operations.
• Analyze and optimize low‑level code to improve performance and efficiency with a strong emphasis on tensor optimization, and run performance profiling to identify and address bottlenecks.
• Collaborate with machine learning engineers and data scientists to integrate optimized kernels and low‑level routines into machine learning frameworks and pipelines.
• Write unit tests, debug kernel‑level code for stability and reliability, and present your project approach, accomplishments, and findings to the team at the end of your internship.

What You Will Learn

• How to take a well‑scoped engineering project related to convolutions and their optimizations on Tenstorrent hardware from idea to implementation with guidance from a dedicated mentor.
• Hands‑on experience building, optimizing, and profiling kernels for convolution‑based operations and tuning low‑level code for performance.
• Practical skills integrating optimized kernels and low‑level routines into machine learning frameworks and pipelines, and hardening them through testing and debugging.
• How to communicate technical work clearly by sharing your observations, approach, and results with the broader team.

Hiring Timelines

This internship opportunity is available throughout our 3 terms with the following corresponding recruitment cycles:

• Winter Term: Mar–May work term, Nov–Jan recruit.
• Summer Term: Aug–Oct work term, Jan–May recruit.
• Fall Term: Oct–Dec work term, Apr–May recruit.

Please note these timelines are for reference only. Actual timelines may vary.

Tenstorrent offers a highly competitive compensation package and benefits, and we are an equal opportunity employer.

At Tenstorrent, we believe the future of computing must be open, which is why our interns don’t just watch from the sidelines - they help build the core of it. We provide a "code-to-career" pipeline where students collaborate with industry experts to solve high-stakes problems in RISC-V and AI hardware-software co-design. By joining us, you are taking an internship to democratize high-performance computers that are accessible to everyone. 

In this role, you will implement state of art ML models on Tenstorrent hardware using Python and C++, focusing on pushing both accuracy and inference speed. You will work hands-on with Tenstorrent’s open-source software stack (tt-metalium, tt-nn, tt-llk), taking models from framework to silicon and iterating on performance. You will own a well-defined engineering project under the guidance of a dedicated mentor, with direct impact on how real workloads run on our chips. We are looking for a minimum of 3 months for this role with the potential for extension to 6 months. 

This role is onsite, based in our Belgrade office.

Who You Are

• Enrolled in the final year of BSc or MSc studies in Computer Science, Computer Engineering, Software Engineering, Electronics, Math, or a related field.
• Solid coding skills in Python and C++, with a basic understanding of machine learning concepts and frameworks.
• You have a passion for programming, are eager to learn, and enjoy solving complex performance and optimization problems.
• You are collaborative, open to feedback, and excited to work closely with experienced engineers and a dedicated mentor.

What We Need

• Implement functional ML models on Tenstorrent hardware using Python and popular ML frameworks like PyTorch.
• Benchmark, analyze, and optimize the performance of the implemented model's inference using existing tools and coding in C++ and Python.
• Collaborate with experienced engineers to validate the accuracy of implemented models and iterate on improvements.
• Contribute to performance optimization efforts where success is measured by achieving both high accuracy and fast execution (inference) of ML models on Tenstorrent hardware.

What You Will Learn

• How to implement state-of-the-art ML models on Tenstorrent hardware using Python, C++, and popular ML frameworks like PyTorch.
• Techniques for benchmarking, analyzing, and optimizing the performance of ML model inference using existing tools and code in C++ and Python.
• How to use (and potentially debug and fix) Tenstorrent’s open-source software libraries, such as tt-metalium, tt-nn, and tt-llk.
• How to collaborate with experienced engineers, apply various problem-solving techniques, and drive a well-defined engineering project under the guidance of a dedicated mentor.

Hiring Timelines

This internship opportunity is available throughout our 3 terms with the following corresponding recruitment cycles:

• Winter Term: Mar–May work term, Nov–Jan recruit.
• Summer Term: Aug–Oct work term, Jan–May recruit.
• Fall Term: Oct–Dec work term, Apr–May recruit.

Please note these timelines are for reference only. Actual timelines may vary.

Join our Models Infra team, where we build the systems that enable reliable development, testing, and release of AI models on Tenstorrent hardware. This team focuses on automation, CI/CD pipelines, infrastructure, and tooling that power large-scale model validation, benchmarking, and release workflows. We are looking for a minimum of 3 months for this role with the potential for extension to 6 months. 

This role is hybrid based in Belgrade, Serbia.

You will work on real-world infrastructure problems under the guidance of experienced engineers and a dedicated mentor.

Who You Are

• Final-year BSc or MSc student in Computer Science, Software Engineering, Electrical Engineering, or a related field
• Comfortable with Python and scripting; familiarity with Bash is a plus
• Interested in infrastructure, automation, CI/CD systems, and developer tooling
• Basic understanding of Docker and containerized environments
• Curious about how large-scale systems are built, tested, and deployed
• Motivated to learn, take ownership, and contribute in a collaborative environment

What We Need

• Contribute to CI/CD pipelines used for building, testing, and releasing AI software and models
• Help automate workflows around model validation, benchmarking, and reporting
• Work with Docker and containerized environments to improve reproducibility and efficiency
• Assist in maintaining and improving infrastructure used by engineers (e.g. runners, build systems, test environments)
• Write clean, maintainable scripts and tools with guidance from senior engineers

What You Will Learn

• How CI/CD systems are designed and scaled for complex AI workloads
• How infrastructure enables reliable model development and release processes
• Best practices for automation, observability, and system reliability
• How containerization and orchestration are used in production environments

Hiring Timelines

This internship opportunity is available throughout our 3 terms with the following corresponding recruitment cycles:

• Winter Term: Mar–May work term, Nov–Jan recruit.
• Summer Term: Aug–Oct work term, Jan–May recruit.
• Fall Term: Oct–Dec work term, Apr–May recruit.

Please note these timelines are for reference only. Actual timelines may vary.

Tenstorrent offers a highly competitive compensation package and benefits, and we are an equal opportunity employer.