Sr. ML Researcher, LLM Algorithmic Optimization

Position: Sr. Staff ML Researcher, LLM Algorithmic Optimization
Join d-Matrix and help build the future of AI inference. We’ve pioneered a memory-centric architecture that brings compute directly into memory, making AI faster, more energy efficient, and accessible on a global scale. From chips and software to rack-scale systems, our team is tackling some of AI infrastructure’s hardest challenges — and shipping breakthrough technology today. If you want to create what comes next and help make infinite inference possible, we’d love to hear from you.

Our culture is built on respect, collaboration, and direct communication. We value humility, we believe our different perspectives lead to better solutions, and we’re looking for people who are driven by execution and energized by hard problems.

Role Overview d-Matrix is seeking a Senior Staff ML Researcher to join our Algorithms team and develop new methods for running large language models efficiently on our DNN accelerators. This is a hands-on research role at the intersection of machine learning, applied mathematics, numerical computing, and AI hardware. You will invent, evaluate, and implement algorithmic techniques that improve LLM inference performance while preserving model quality, with a focus on challenges such as numerical precision, model compression, memory efficiency, and efficient execution on accelerator hardware.

You will work closely with mathematicians, ML researchers, ML engineers, compiler engineers, and hardware architects to translate research ideas into practical solutions for cutting-edge generative AI workloads.

What You Will Do Research and develop algorithmic and numerical techniques that improve the latency, throughput, memory efficiency, and accuracy of large language model inference on d-Matrix DNN accelerators.

Design and evaluate methods such as low-precision quantization, model compression, sparsity, pruning, distillation, low-rank approximation, and other techniques for efficient neural-network execution.

Optimize key transformer inference workloads, including matrix operations, attention mechanisms, and KV-cache utilization, based on model characteristics and hardware constraints.

Analyze tradeoffs among model quality, numerical precision, memory footprint, compute efficiency, and system performance.

Build high-quality research prototypes and evaluation frameworks in Python to test new ideas across relevant models, datasets, and workloads.

Partner with hardware, compiler, and software teams to map algorithms effectively to accelerator capabilities, including supported data types, memory hierarchy, data movement, and compute architecture.

Stay current with advances in efficient LLM inference, neural-network optimization, numerical methods, and hardware-aware machine learning, and apply relevant developments to d-Matrix products.

What You Will Bring Master's degree or PhD in Computer Science, Mathematics, Statistics, Physics, Electrical Engineering, or a related quantitative field, with 5+ years of relevant hands-on experience.

Strong foundation in machine learning and applied mathematics, with the ability to apply mathematical or numerical methods to practical ML problems.

Hands-on experience developing and evaluating machine-learning algorithms, models, or research prototypes.

Strong Python programming skills and experience with object-oriented code design.

Experience with modern machine-learning frameworks such as PyTorch, JAX, or Tensor Flow.

Experience improving the performance, efficiency, or quality of machine-learning models through algorithmic or numerical techniques.

Familiarity with neural-network architectures; experience with transformers, LLM inference, or hardware-aware ML optimization is advantageous but not required.

Ability to design rigorous experiments, analyze…