About TetraMem
At TetraMem, we are at the forefront of next-generation in-memory computing technology, revolutionizing the way AI hardware processes data. Our mission is to push the boundaries of performance, energy efficiency, and scalability, empowering the future of artificial intelligence and machine learning applications.
Founded by a team of industry veterans, researchers, and innovators, TetraMem is backed by cutting-edge research and strong partnerships with key players in the semiconductor industry. With offices in the U.S. and Singapore we are growing rapidly and expanding our global footprint.
About the Team
We are looking for a Machine Learning Engineer Intern to work on how neural networks are trained, compressed, and deployed on TetraMem’s analog compute-in-memory chips. You will work on real models from our model zoo. You will take them from a PyTorch checkpoint to a version that runs on our hardware, and you will measure the accuracy and efficiency trade-offs along the way. You will work closely with the ML model, compiler, and hardware teams.
Job Responsibilities
- Assist in training, fine-tuning, and adapting neural network models, including computer vision, audio/speech, and compact language models for compute-in-memory hardware platforms.
- Implement and evaluate model compression techniques, including post-training quantization (PTQ), quantization-aware training (QAT), mixed-precision assignment, pruning, and knowledge distillation.
- Develop hardware-aware training methods that make models robust to low-precision weights and analog non-idealities.
- Analyze model graphs for operator coverage, rewrite or replace unsupported operators, and export models for the compiler toolchain.
- Profile accuracy, latency, and memory on simulation and hardware, and find where accuracy is lost.
- Write clean, tested Python (and C++ where needed) for model training, quantization, and evaluation toolchain.
- Document experimental methodologies, analyze results, and technical findings through technical reports and team presentations.
Required Qualifications
- Currently pursuing a BS, MS, or PhD in Computer Science, Electrical Engineering, or a related field.
- Hands-on experience training and evaluating neural networks using PyTorch through research, internships, or substantial projects beyond course tutorials.
- Familiarity with at least one model optimization technique such as quantization (PTQ or QAT), pruning, distillation, or efficient architecture design.
- Solid understanding of deep learning fundamentals, including common neural network layers, normalization, attention mechanisms, backpropagation, and numerical precision (FP32/FP16/INT8).
- Strong Python skills and familiarity with software development practices, including vision control, debugging, testing, and writing maintainable code.
- Ability to read and understand technical research papers, implement published methods, and evaluate their applicability to new problems.
Preferred Qualifications
- Experience deploying models to edge or embedded targets (e.g., ONNX Runtime, TFLite/LiteRT, ExecuTorch, TensorRT).
- Familiarity with ML compilers or graph IRs (ONNX, TVM, MLIR).
- C++ experience for inference runtimes or performance-critical code.
- Experience with audio/speech models (keyword spotting, speech enhancement, ASR) or compact vision models.
- Background in hardware-aware ML, noise-robust training, or analog/in-memory computing.
- Publications, open-source contributions, or competition results in efficient ML.
- M.S. or Ph.D. in Computer Science, Electrical Engineering, or a related field.
Annual Base Salary Range: $34.00 - $45.00 USD/hr
TetraMem celebrates diversity and is committed to creating an inclusive environment for all employees. We are proud to be an Equal Opportunity Employer and welcome applicants from all backgrounds. Qualified candidates will receive consideration for employment without regard
to race, color, religion, creed, sex, gender identity or expression, sexual orientation, national origin, ancestry, age, marital status, medical condition, disability, genetic information, military or veteran status, or any other characteristic protected by applicable federal, state, or local law.
TetraMem is committed to providing reasonable accommodations to qualified applicants with disabilities throughout the recruitment process. Applicants requiring accommodation may contact Human Resources for assistance at recruiting@tetramem.com
To ensure a fair, consistent, and efficient hiring process, all candidates must apply through TetraMem’s official ClearCompany Applicant Tracking System (ATS). Applications submitted through the ATS allow our hiring team to evaluate candidates using a standardized process and ensure timely communication throughout the recruitment process. To promote equal consideration for all applicants, applications submitted outside of the ClearCompany ATS, including direct emails, LinkedIn messages, or unsolicited submissions to employees, may not be reviewed or considered.
We encourage all interested candidates to apply through the official TetraMem Careers page.