Description

Harvard University


Title: Postdoctoral Fellow in On-Premise Computing for Autonomous Vehicles (Computer Architecture, Machine Learning and Runtime Systems)

School: Harvard John A. Paulson School of Engineering and Applied Sciences

Department_Area: Electrical Engineering/Computer Engineering/Computer Science

Position Description: Project

Deep learning plays an essential role in the operation of an autonomous vehicle (AV), allowing for automated detection, prediction, mapping, and planning. During the vehicle's operation, data is obtained through a myriad of sensors in an AV-including RADAR , LIDAR , cameras, and other advanced driver assistance systems ( ADAS ) sensors. These sensors generate a vast amount of data concurrently, which need real-time processing (latency-bound throughput) for vehicle safety. A crucial challenge meeting this requirement is the simultaneous need for low-power consumption.

The main objective of the project is to develop a complete end-to-end high-performance DNN system for on-premise computing applications-mainly for a SWaP-constrained AV-using hybrid electro-photonic accelerators. We propose to design and prototype a complete electro-photonic computing (EPiC) system (CPUs + accelerators), integrate it with the sensors in AV, and demonstrate its capability to perform perception, mapping, and planning while overcoming the power and performance limitations of CMOS -only computers. As our end goal, we plan to demonstrate a fully autonomous buggy that uses our EPiC system.

This project is a collaboration among Lightmatter, Boston University, and Harvard University. The Lightmatter team is led by Dr. Darius Bunandar, the Boston University team is led by Prof. Ajay Joshi, and the Harvard University team is led by Prof. Vijay Janapa Reddi.

Role

Our team has two postdoctoral researcher openings. The postdoctoral researchers will be jointly supervised by Prof. Joshi at Boston University and Prof. Reddi at Harvard University. The appointment is for one year with an optional second year, subject to performance and availability of funds. The expected start date is January 1, 2022.

Responsibilities

The responsibilities of the postdoctoral researcher include:

• Work closely with the graduate students at Boston University and Harvard University, and the engineers at Lightmatter to complete the deliverables of the project.
• Publish research papers in top-tier conferences, and present the work at conferences, other universities, and companies.
• Participate in developing new research projects and writing grant proposals.

Basic Qualifications: Applicants are expected to have a Ph.D. in EE, CE, or CS (by the start date) with expertise in at least one (or more) of the following areas:

• Computer Architecture/Systems: Design, modeling, simulation, and/or physical design of heterogeneous system/processor architectures; Silicon-photonic computing architectures; Silicon-photonic network architectures
• Machine Learning Algorithms/Systems: Experience in design and use of ML algorithms; Experience in using ML for designing computing systems
• Autonomous Vehicles/Systems: Design, integration, and evaluation of AI models for autonomous driving systems; Experience with AV simulators and the AV stack.

Additional Qualifications: Expertise in two or more of the above areas is a plus. Also, hands-on experience with design and prototyping of complete computing systems will be considered a plus.

Special Instructions: Please pay close attention to the following prior to uploading your documents:

1. CV with a list of your publications.
2. Cover letter summarizing how your background/experiences makes you a good fit for the project, and your career goals.
3. Undergraduate and graduate transcripts.

Contact Information: Sarah Gayer

Contact Email: [email protected]


Minimum Number of References Required: 2

Maximum Number of References Allowed: 5

Keywords: On-Premise Computing Autonomous Vehicles Computer Architecture Machine Learning Runtime Systems

Supplemental Questions: Required fields are indicated with an asterisk (*).

PI278014377