About the role#
We are looking for a Software Intern to help build tools, frameworks, and applications that allow neural network models to run on our analog compute-in-memory chips. You will work at the intersection of software, hardware, and artificial intelligence.
What you'll do#
- Develop, optimize, and maintain Python and C++ software for neural network model compression, conversion, and deployment.
- Design tools to improve machine learning model efficiency, such as quantization, pruning, graph optimization, and memory reduction.
- Adapt machine learning models to improve compatibility, performance, and power efficiency on Compute-in-Memory and Analog AI hardware.
- Build software frameworks, APIs, and runtime components to support AI model deployment on edge and embedded systems.
- Perform software design, implementation, debugging, and performance profiling to optimize system throughput and resource use.
- Collaborate with AI researchers, hardware engineers, and system architects to validate hardware-software co-design.
- Evaluate emerging machine learning models and deployment techniques to enhance AI inference on new semiconductor platforms.
- Participate in code reviews, contribute to automated testing, and maintain technical documentation.
- Troubleshoot software and system issues across the AI stack, including model conversion pipelines and hardware acceleration frameworks.
- Support research activities through technical presentations, publications, and cross-functional collaboration.
What you'll need#
- Currently pursuing a degree in Computer Science, Electrical Engineering, or a related field.
- Programming experience in Python, C++, or similar languages.
- Knowledge of data structures, algorithms, and software architecture.
- Familiarity with AI/ML frameworks like TensorFlow or PyTorch is a plus.
- Strong problem-solving skills and a willingness to learn.
Location & details#
- Location: San Jose, California.
- Modality: On-site.
- Role type: Full-time.
- Compensation: $35.00 to $45.00 per hour, based on education, experience, and technical skills.
- Term: Rolling.
About TetraMem - Accelerate The World
TetraMem develops analog computing hardware for artificial intelligence applications. The company focuses on power efficiency and performance for modern computing tasks. It is based in San Jose, California. Founded in 2018, the firm operates as a private entity with 51 to 200 employees.
How to get in at TetraMem - Accelerate The World
Applying early to TetraMem gives you a distinct advantage because recruiters review applications in the order they arrive. Intern Insider sends an instant alert the moment a role matching your target is published, so you can submit your materials before the applicant pile grows. You gain a better chance of being seen by acting quickly. Reaching out to the right person at TetraMem often beats waiting in a digital queue. Intern Insider surfaces the recruiters behind the company roles so you can contact them directly to ask about the position or a referral. This direct approach often improves your response rates compared to a standard submission.
