IBM Research scientist in SAN JOSE, California

IBM’s Brain-Inspired Computing team at IBM Research - Almaden has built a first-of-a-kind modular, scalable, non-von Neumann, ultra-low power, cognitive computing architecture (TrueNorth) and associated end-to-end software ecosystem. We are building state-of-the-art digital spiking neuromorphic chips and systems (large-scale and mobile) to solve real-time sensory problems.We seek team members with varied backgrounds and experiences for positions in software engineering, systems design, chip design, algorithm/application development, theoretical understanding and education/training. Ideal candidates will have expertise in several of the following areas:Neuromorphic hardware design:

  • VLSI design including logic design (synchronous and/or asynchronous), physical design, integration, verification, and validation

  • Printed Circuit Board (PCB) design/debug, Field Programmable Gate Array (FPGA) development/debug

  • Large-scale system design

Software/Firmware:

  • Real-time embedded software/firmware development, Linux kernel/device drivers, system level simulation and optimization

  • Parallel programming using tools such as Message Passing Interface (MPI), Compute Unified Device Architecture (CUDA), OpenMP, C++11 threads

  • User interface design, testing, and deployment

  • Expert level programming skills in C++11, MATLAB, Python

  • Experience with TensorFlow / Caffe / MatConvNet

  • Software maintenance and source control ( Git, Subversion, ClearCase), bug tracking (Github, Jira, Bugzilla), and collaboration (Confluence, MoinMoin)

Neuromorphic Algorithms and Applications:

  • Mapping neural networks to custom hardware

  • Neural Networks, Deep Learning, Convolutional Networks, Recurrent Networks, Machine Learning, Pattern Recognition, or Probabilistic Graphical Models

  • Experience developing, testing, and deploying systems for image processing, speech, robotics, medical imaging, or other real-world applications

  • Information theoretical system models, high dimensional non-linear dynamical systems, complex adaptive systems

Education / Training:

  • Demonstrated ability to conduct in-person and on-line training sessions, and to help develop and expand the training curriculum.

  • Experience in developing / facilitating MOOC-style delivery

  • At least 1 year experience in MATLAB and C++

  • At least 1 year experience in machine learning

  • Basic knowledge in large scale neural networks

  • English: Intermediate

IBM is committed to creating a diverse environment and is proud to be an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, gender, gender identity or expression, sexual orientation, national origin, genetics, disability, age, or veteran status. IBM is also committed to compliance with all fair employment practices regarding citizenship and immigration status.