Auto AI Systems Engineer

We are looking for experts with strong background in deep learning (DL) field to design state of the art low level perception (LLP) models with the focus on accuracy-latency pareto optimality. This entails comprehending SOTA research in LLP combined with network deployment on Qualcomm Ride platform for L2/L3 ADAS/Autonomous driving.

The job requires candidate to be through in recent advancement in Vision transformers (Cross attention, Self-attention), lifting 2D features to BEV space and their applications to multi modal fusion. The job gives extensive opportunity to collaborate with advanced R&D teams of leading Automotive OEMs as well as QCOM internal stack teams.  The team is responsible for improving speed, accuracy, power-consumption, and latency of deep networks running on Snapdragon Ride AI accelerators.

Knowledge of machine learning algorithms, especially related to automotive use-cases (autonomous driving, vision and lidar processing ML algorithms) are necessary.

Research experience with development of efficient networks, various Neural Architecture Search (NAS) techniques, network quantization and pruning is an added plus.

Strong communication and interpersonal skills are required and must be able to work well with various horizontal AI teams.

Preferred Qualifications:

• PhD in related field with 1+ years of relevant experience, master’s with 3+ years, or Bachelor of engineering with 4+ years of relevant experience.

• Good at software development with excellent analytical, development, and problem-solving skills.

• Strong understanding of Machine Learning fundamentals

• Hands-on experience with deep learning network design and implementation. Ability to define network from scratch in PyTorch, ability to add new loss function, modify network with torch.fx. Adept at version control system like GIT.

• Experience in neural network quantization, compression, pruning algorithms.

• Experience in deep learning kernel/compiler optimization

• Strong communication skills