Manager, Software Engineering-Kernels

d-Matrix Corporation

Job Overview

Location

Bangalore, Indiana, USA

Job Type

Full-time

Full Job Description

📋 Description

• d-Matrix Corporation is at the vanguard of generative AI, dedicated to transforming technology through groundbreaking software and hardware innovation. We are seeking a highly skilled and motivated Manager, Software Engineering-Kernels to join our dynamic team in Bangalore. This pivotal role is central to productizing the software stack for our cutting-edge AI compute engine, pushing the boundaries of what's possible in AI hardware-software co-design.
• As a Manager, Software Engineering-Kernels, you will be instrumental in the development, enhancement, and maintenance of sophisticated software kernels tailored for next-generation AI hardware. Your expertise will be crucial in translating complex AI algorithms and computational graphs into efficient, high-performance code that leverages the unique capabilities of our specialized hardware.
• You will possess a profound understanding of diverse hardware architectures and excel at mapping computational tasks and AI models to these architectures. This includes a deep appreciation for how to optimize the execution of AI frameworks' computational graphs on the underlying hardware, ensuring maximum performance and efficiency.
• This role demands a comprehensive grasp of the full-stack toolchain, from low-level kernel development to higher-level software integration. You will navigate the intricate trade-offs inherent in hardware-software co-design, making informed decisions to balance performance, power, and area.
• A key aspect of your responsibility will be to build and scale software deliverables within aggressive development timelines. This requires meticulous planning, efficient execution, and a proactive approach to problem-solving.
• You will collaborate closely with a talented team of compiler experts to build and refine our compiler infrastructure. This cross-functional collaboration extends to working hand-in-hand with other software specialists (ML, systems) and hardware engineers (mixed-signal, DSP, CPU) across the company, fostering a cohesive and innovative development environment.
• Your contributions will directly impact the performance and capabilities of our AI compute engine, enabling breakthroughs in generative AI and other computationally intensive applications.
• You will be responsible for architecting and implementing low-level software components that form the foundation of our AI hardware's software stack. This includes optimizing critical computational kernels for AI workloads, such as matrix multiplications (GEMMs), convolutions, BLAS operations, and SIMD-accelerated functions like softmax, layer normalization, and pooling.
• A significant part of the role involves understanding and optimizing the mapping of computational graphs generated by popular AI frameworks (like TensorFlow and PyTorch) onto our specialized hardware architecture. This requires a deep dive into the data flow and computational patterns of these graphs.
• You will engage in hardware-software co-design discussions, providing crucial software insights to hardware architects to ensure that the hardware is designed with software performance and programmability in mind. This iterative process is key to achieving optimal system-level performance.
• The role requires hands-on development and debugging of software kernels, often involving performance profiling and optimization at the micro-architectural level.
• You will contribute to the development and maintenance of the full software toolchain, ensuring a seamless experience for developers utilizing our AI compute engine.
• This position offers a unique opportunity to work on the cutting edge of AI hardware and software, contributing to a product that will shape the future of artificial intelligence. You will be part of a culture that values respect, collaboration, humility, and direct communication, where diverse perspectives lead to superior solutions. If you are passionate about tackling complex challenges and driven by execution, this is your playground to shape the endless possibilities of AI.

🎯 Requirements

• MS or PhD in Computer Engineering, Math, Physics, or a related field with 10+ years of industry experience.
• Strong grasp of computer architecture, data structures, system software, and machine learning fundamentals.
• Proficient in C/C++ and Python development within a Linux environment, utilizing standard development tools.
• Experience implementing algorithms for specialized hardware (FPGAs, DSPs, GPUs, AI accelerators) using relevant libraries (e.g., CUDA).
• Experience implementing operators common in ML workloads (GEMMs, Convolutions, BLAS, SIMD operators for softmax, layer normalization, pooling, etc.).
• Experience with development for embedded SIMD vector processors (e.g., Tensilica).

🏖️ Benefits

• Competitive salary and equity package.
• Comprehensive health, dental, and vision insurance.
• Generous paid time off and holidays.
• Opportunity to work on groundbreaking AI technology.
• Collaborative and inclusive work environment.
• Professional development and growth opportunities.

Skills & Technologies

Python

Linux

TensorFlow

PyTorch

Hybrid

Degree Required

Ready to Apply?

Apply Externally

You will be redirected to an external site to apply.

d-Matrix Corporation

Visit Website

About d-Matrix Corporation

d-Matrix designs silicon for high-efficiency AI inference at scale. Its Corsair compute platform combines in-memory computing with a digital approach to slash latency and energy use in transformer and generative workloads. Targeting hyperscale data centers and edge deployments, the company offers hardware and software stacks that integrate into existing AI pipelines. Founded in 2019 and headquartered in Santa Clara, California, d-Matrix serves cloud and enterprise customers seeking cost-effective alternatives to GPUs for large language model serving.

View Company Profile