AI Framework & Inference Engineer

Black Sesame; San Jose, Northern (CA, KY); Hybrid; USD 150,000 - 190,000; Full time

Job summary

Black Sesame seeks an experienced AI/ML engineer to deploy AI inference and end-to-end enablement, AI framework integration, model accuracy, and performance tuning. You will develop high-quality software that enables state-of-the-art AI inference on BST Intelligence processors.

Responsibilities include building deep learning infrastructure, data pipelines, and real-time deployment pipelines, with a focus on low-precision inference, quantization, and continual latency/accuracy improvements.

Qualifications

• MS or Ph.D. in Computer Science, Computer Engineering, Applied Math, or related field.
• Ability to work independently, define project goals and scope, and lead your own development effort.
• Strong Python or C/C++ programming and software design skills, including debugging, performance analysis, and test design.
• Experience with Deep Learning Frameworks such as PyTorch, TensorFlow, and MXNet.
• Experience with model acceleration techniques such as deep learning quantization, model pruning, and model distillation.
• Nice-to-have: Experience with numerical methods.
• Nice-to-have: Knowledge of computer architecture.
• Nice-to-have: Experience with AI compilers.
• Nice-to-have: Experience in model deployment within the autonomous driving industry.

Responsibilities

• Contribute to deep learning infrastructure, data pipelines, tools and workflows that lay the foundation for building AI at scale.
• Writing software to deploy AI models and pipelines in real time applications (inference).
• Apply low precision inference, quantization, and compression of DNNs.
• Continuously improve inference latency, accuracy and power consumption of DNNs.
• Stay up to date with the latest research and innovations in deep learning, implement and experiment with new ideas

Skills

Python

C/C++

Software design

PyTorch

TensorFlow

MXNet

Education

MS or Ph.D. in Computer Science / Computer Engineering / Applied Math or related field

Tools

PyTorch

TensorFlow

MXNet

Job description

Black Sesame seeks an experienced AI/ML engineer to deploy AI inference and end-to-end enablement, AI framework integration, model accuracy, and performance tuning. You will develop high-quality software that enables state-of-the-art AI inference on BST Intelligence processors.

Responsibilities include building deep learning infrastructure, data pipelines, and real-time deployment pipelines, with a focus on low-precision inference, quantization, and continual latency/accuracy improvements.