The posting
At d-Matrix, we are focused on unleashing the potential of generative AI to power the transformation of technology. We are at the forefront of software and hardware innovation, pushing the boundaries of what is possible. Our culture is one of respect and collaboration.
We value humility and believe in direct communication. Our team is inclusive, and our differing perspectives allow for better solutions. We are seeking individuals passionate about tackling challenges and are driven by execution. Ready to come find your playground? Together, we can help shape the endless possibilities of AI.
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 TensorFlow.
- 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 results, and communicate technical findings clearly to cross-functional partners.
Equal Opportunity Employment Policy
d-Matrix is proud to be an equal opportunity workplace and affirmative action employer. We’re committed to fostering an inclusive environment where everyone feels welcomed and empowered to do their best work. We hire the best talent for our teams, regardless of race, religion, color, age, disability, sex, gender identity, sexual orientation, ancestry, genetic information, marital status, national origin, political affiliation, or veteran status. Our focus is on hiring teammates with humble expertise, kindness, dedication and a willingness to embrace challenges and learn together every day.
d-Matrix does not accept resumes or candidate submissions from external agencies. We appreciate the interest and effort of recruitment firms, but we kindly request that individual interested in opportunities with d-Matrix apply directly through our official channels. This approach allows us to streamline our hiring processes and maintain a consistent and fair evaluation of al applicants. Thank you for your understanding and cooperation.
