THE ROLE: SR. PRINCIPAL/TECHNICAL DIRECTOR - AI SOC ARCHITECT
If you are following the evolution of the leading approach in deep learning powered AI, the renaissance in NLP as well as the next disruption in computer vision, you likely know it’s all about Transformer based models.. They are powering neural nets with billions to trillions of parameters and existing silicon architectures (including the plethora of AI accelerators) are struggling to varying degrees to keep up with exploding model sizes and their performance requirements. More importantly, TCO considerations for running these models at scale are becoming a bottleneck to meet exploding demand. Hyperscalers are keen on how to gain COGS efficiencies with the trillions of AI inferences/day they are already serving, but certainly for addressing the steep demand ramp they are anticipating in the next couple of years. d-Matrix is addressing this problem head on by developing a fully digital in memory computing accelerator for AI inference that is highly optimized for the computational patterns in Transformers. The fully digital approach removes some of the difficulties of analog techniques that are most often touted in pretty much all other in-memory computing AI inference products. d-Matrix’s AI inference accelerator has also been architected as a chiplet, thereby enabling both a scale-up and scale-out solution with flexible packaging options. The d-Matrix team has a stellar track record in developing and commercializing silicon at scale as senior execs at the likes of Inphi, Broadcom, and Intel. Notably, they recognized early the extremely important role of programmability and the software stack and are thoughtfully building up the team in this area even since before their Series A. The company has raised $44m in funding so far and has 70+ employees across Silicon Valley, Sydney and Bengaluru.
We want to build a company and a culture that sustains the tests of time. We offer the candidate a very unique opportunity to express themselves and become a future leader in an industry that will have a huge influence globally. We are striving to build a culture of transparency, inclusiveness and intellectual honesty while ensuring all our team members are always learning and having fun on the journey. We have built the industry’s first highly programmable in-memory computing architecture that applies to a broad class of applications from cloud to edge. The candidate will get to work on a path breaking architecture with a highly experienced team that knows what it takes to build a successful business.
The role: Principal/Technical Director - AI SOC Architect
The AI SOC Architecture Team is responsible driving Silicon roadmap and directions, architectural explorations, hardware-software co-design, performance projections and modeling, cross-team collaborations and academic outreach. You will be joining a team of exceptional people enthusiastic about researching and developing state-of-the-art efficient deep learning techniques tailored for d-Matrix's AI compute engine. We are seeking SoC Architect to lead our SoC Technologies Definition. This exciting opportunity requires strong technical knowledge and exceptional leadership. You will drive the Architecture in conjunction with RTL & DV engineers of multiple technologies including but not limited to performance and power efficiency, thermal management, memory, interconnects & packaging to deliver exceptional product experiences across our entire portfolio.
• Lead the design and delivery of SoC requirements and architecture that delivers exceptional customer experiences.
• Analysis of AI workloads such as transformers & CNNs across existing and new emerging product categories to identify bottlenecks and opportunities for improvement.
• Identify areas of improvement and drive the architecture to deliver the product. Design, implement and evaluate efficient deep neural network architectures and algorithms for d-Matrix's AI compute engine
• Conduct research to guide hardware/software co-design of SIMD engine, control plane, data reshape engine, data convertor blocks, NoC substrate and many other blocks
• Work on various phases of our flagship product (Corsair I and II) ranging from performance projection, performance modeling, performance correlation and performance debug aspects.
• Develop and maintain tools for high-level simulation and research to enable architectural exploration of current and future generation products
• Engage and collaborate with SW team to meet stack development milestones
• Port customer workloads, optimize them for deployment, generate reference implementations and evaluate performance
• Report and present progress timely and effectively
• Contribute to publications of papers and intellectual properties
• MS in Computer Science, Electrical and Computer Engineering, or a related scientific discipline with 10+ year of relevant experience in compute architecture and system design area.
• A problem solver, self-starter, be able to effectively multi-task and simplify complex problems to come up with elegant and efficient solution (no compromise here!)
• 10 or more years of demonstrated experience leading Architecture or Design Development of SoCs.
• Expert knowledge of AI SoC Architecture, requirements, and definition.
• Be able to identify potential architectural issues and design flaws early in the design phase to provide effective solutions and recommendations.
• Experience with CPU, GPU, ASIC and ML accelerator architecture exploration and architectural modeling.
• High proficiency in performance modeling, ranging from simple analytical model to complex cycle accurate performance model and correlation
• Deep, wide and current knowledge in machine learning and modern deep learning is required.
• Hands-on experience with CNN, RNN, Transformer neural network architectures.
• Experience with specialized HW accelerator systems for deep neural network is preferred.
• PhD (preferred) in Computer Science, Electrical and Computer Engineering, or a related scientific discipline with 10+ year of relevant experience in compute architecture and system design area.
•High proficiency in algorithm analysis, data structure, and Python programming is required. Proficiency with C/C++ programming is preferred.
•Passionate about AI and thriving in a fast-paced and dynamic startup culture.