Title: ML Inference Engineer - NEON (Remote in United States Negotiable)
Company: Samsung Research America (SRA)
Location: Mountain View, CA (Remote in United States Negotiable)
We are NEON, a subsidiary of Samsung dedicated to creating Artificial Humans who interact with you in ways indistinguishable from the real world. Our NEONs (Neo humaNs) draw inspiration from the most natural of interfaces: interaction with another human being. Bringing together a world-class R&D team of researchers, developers, and engineers, that are building production technology at the cutting edge of artificial intelligence, machine learning, real-time computing, conversational agents, computer graphics, design, and more.
NEONs hold the potential to advance our digital world while preserving the elements of human interaction that are meaningful to all of us. If you share that dream – if you want to make the visions you saw in Her, Blade Runner, and more into tangible reality – and are passionate about taking such ideas into handcrafted renderings, we would love to hear from you!
We are looking for a highly skilled, thoughtful, and collaborative ML Inference Engineer to help design and develop the next generation of NEONs and delivering this innovative technology to a wide user base. As a part of the technical team, you’ll solve challenging problems and provide input into both product roadmaps and development approaches. Our team is based in Mountain View, California. However, remote work is negotiable for this position!
- Optimize inference pipeline consisting of multiple Deep Learning models
- Conduct performance analysis, optimization, and tuning of Deep Learning models
- Follow development and feature updates of model optimization tools such as TensorRT
- Provide feedback to the network architecture and hardware setup for better performance
- Closely work with other software engineers and researchers to guide the direction of ML inference pipeline
- Master’s or PhD in machine learning, software engineering, or experience in a related field or equivalent practical experience and training
- 2+ years of experience in this field
- Extensive experience in ML model analysis, optimization, and tuning
- Experience with GPGPU programming, in CUDA, OpenCL or Metal
- Experience with Neural Network inference frameworks, such as TensorRT, OpenVINO, CoreML, or TensorFlow
- Fluent in one of the popular Deep Learning frameworks such as Pytorch or Tensorflow
- Experience with High-Performance & Parallel Computing on CPU/GPU.
- Familiarity with TensorRT is preferred
Incumbent must make themselves available during core business hours.
This position will be performed in an office setting. The position will require the incumbent to sit and stand at a desk, communicate in person and by telephone, frequently operate standard office equipment, such as telephones and computers, and reach with hands and arms.
Samsung is committed to encouraging a diverse workplace and proud to be an equal opportunity employer. As we highly value diversity in our current and future employees, we do not discriminate (including in our hiring and promotion practices) based on race, religion, color, national origin, gender, gender expression, sexual orientation, age, marital status, veteran status, disability status or any other characteristic protected by law.
If you have a disability or special need that requires accommodation, please let us know.
All your information will be kept confidential according to EEO guidelines.