Machine Learning Intern (2027)

Tetramem•San Jose, CA

About The Position

TetraMem is seeking a Machine Learning Engineer Intern to work on training, compressing, and deploying neural networks on its analog compute-in-memory chips. The intern will work with models from TetraMem’s model zoo, convert PyTorch checkpoints into versions that run on the hardware, and measure accuracy and efficiency trade-offs. The role involves close collaboration with the ML model, compiler, and hardware teams.

Requirements

  • 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 PTQ, 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 version 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.

Nice To Haves

  • Experience deploying models to edge or embedded targets, such as ONNX Runtime, TFLite/LiteRT, ExecuTorch, or TensorRT.
  • Familiarity with ML compilers or graph IRs, such as ONNX, TVM, or MLIR.
  • C++ experience for inference runtimes or performance-critical code.
  • Experience with audio/speech models, such as keyword spotting, speech enhancement, or ASR, or with 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.
  • An M.S. or Ph.D. in Computer Science, Electrical Engineering, or a related field.

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 to 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 identify where accuracy is lost.
  • Write clean, tested Python and, where needed, C++ for model training, quantization, and evaluation tools.
  • Document experimental methodologies, analyze results and technical findings, and present them to the team.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service