AI Systems Hardware Engineer

Qualcomm Technologies, Inc.

Engineering Group, Engineering Group > ASICS Engineering

We are seeking a highly skilled engineer to enable highly optimized mapping of AI workloads to Qualcomm’s next generation system-technology solutions for the slowing Moore’s law era. The focus is on identifying the system and technology bottlenecks for the state‑of‑the‑art and emerging AI workloads e.g. the mixture-of-experts (MoE), multi‑tenant vector databases, multimodal physical AI etc.. The E2E system KPIs for mapping these emerging AI workloads include the power, performance and TCO of the entire system encompassing the SoC, memory and networking.

The primary role of the candidate is to map the workloads using both internal and external tools to Qualcomm’s next‑gen AI accelerator systems and carry out what‑if scenarios of optimizing different underlying components e.g. SoC, memory, networking and other technology features for the best power‑performance‑TCO trade‑off. The candidate also needs to ensure which AI workloads are relevant for the different business units (BUs) from datacenters to physical AI to computing devices.

To drive these technologies the person will collaborate with high‑level representatives across functional teams (e.g. Architecture, product management, SW teams) to enable an implementation strategy that meets system requirements.

The preferred location for this position is San Diego, CA. Qualcomm's Santa Clara and Austin locations may also be considered. The position is expected to comply with the company's onsite work policy and is not eligible for remote work.

• Bachelor's degree in Science, Engineering, or related field and 6+ years of ASIC design, verification, validation, integration, or related work experience.
• Master's degree in Science, Engineering, or related field and 5+ years of ASIC design, verification, validation, integration, or related work experience.
• PhD in Science, Engineering, or related field and 4+ years of ASIC design, verification, validation, integration, or related work experience.

• Thorough understanding of E2E system KPI dependency e.g. power, performance and TCO of emerging AI workloads mixture‑of‑experts (MoE), multi‑tenant vector databases, multimodal physical AI.
• Ability to quickly map newer workloads onto Qualcomm systems using internal and external tools so high proficiency in scripting (python or similar) is required.
• Great knowledge of state‑of‑art workloads across multiple BUs.
• Master's or Ph.D. in Electrical Engineering, Computer Science, or a related field
• Exceptional creativity to innovate new ideas and develop innovative products/ processes without established objectives or known parameters.
• Verbal and written communication skills to convey highly complex and/or detailed information. Will require strong negotiation and influence with large groups or high‑level constituents
• Ability to work independently and as part of a team
• Most tasks do not have defined steps; simultaneous use of multiple mental abilities is generally required to determine the best approach
• Deductive and inductive problem solving is required; multiple approaches may be taken/necessary to solve the problem; often information is missing or conflicting; advanced data analysis and interpretation skills are required.

Qualcomm is an equal opportunity employer. If you are an individual with a disability and need an accommodation during the application/hiring process, rest assured that Qualcomm is committed to providing an accessible process. You may e-mail disabili or call Qualcomm's toll‑free number found here. Upon request, Qualcomm will provide reasonable accommodations to support individuals with disabilities…