Deep Learning Engineer - AI Engine

Job Description

Description

Xilinx is now part of Advanced Micro Devices (AMD).

At AMD, we push the boundaries of what is possible. We believe in changing the world for the better by driving innovation in high-performance computing, graphics, and visualization technologies – building blocks for gaming, immersive platforms, and the data center.

Developing great technology takes more than talent: it takes amazing people who understand collaboration, respect, and who will go the “extra mile” to achieve unthinkable results. It takes people who have the passion and desire to disrupt the status quo, push boundaries, deliver innovation, and change the world. If you have this type of passion, we invite you to take a look at the opportunities available to come join our team.

Job Description:

In this role, the individual will be responsible for creating system architecture specification that includes hardware and software architecture, performing system level design creation, verification and validation on a target Xilinx device. The individual will be involved in system development using video analytics and Xilinx ML IP library, developing SW framework and application to validate functionality and performance of the intelligent video pipeline on pre-silicon/target silicon device ensuring silicon architecture goals can be met. This role expects the individual to work across cross-functional teams to resolve IP and SW dependencies and minimize schedule risk. This role also requires creating customer facing documentation for the products that will be delivered to the customers. The team is dynamic and fast paced offering each of its members tremendous personal opportunity to grow their knowledge and skills in complex problem solving, product development and system engineering

Job Description

The AI Engine systems team plays a key role in the development of C/C++ based kernels for AI/ML systems, mapping a CNN/RNN/NLP network architecture into Xilinx AI Engine devices, system integration and performance characterization of Xilinx’s advanced device families.

In this role, the individual will be responsible for mapping a specific compute algorithm into Xilinx AI Engine device, development of C/C++ kernel that performs the specific functions in an algorithm, performance simulations and optimization, system development using video analytics and Xilinx ML IP library, developing SW framework and application to validate functionality and performance of the intelligent video pipeline on pre-silicon/target silicon device ensuring silicon architecture goals can be met. This role expects the individual to work across cross-functional teams to resolve IP and SW dependencies and minimize schedule risk. This role also requires creating customer facing documentation for the products that will be delivered to the customers. The team is dynamic and fast paced offering each of its members tremendous personal opportunity to grow their knowledge and skills in complex problem solving, product development and system engineering.

Essential Duties & Responsibilities:

• Map evolving AI/ML compute functions into AI Engine’s scalar and vector processor
• Create reference model using Matlab/Python libraries and verify functionality of kernels
• Performance simulation and optimization of kernels
• Develop and validate VLIW-based processor systems on both pre-Silicon and post-Silicon platforms based on different use case applications
• Solve challenging technical problems with complex SoC based systems that integrate robust algorithms and features
• Work on systems including image processing pipelines, intelligent processing (machine learning) in the DSP processor systems, compressing/decompressing that require both a system specific, and an algorithmic knowledge base
• Lead the discussion in the AI Engines Technical Solutions Team forum
• Be involved in all aspects of integrated product development, including design, prototyping, implementation, testing, and product demonstration
• Provide feedback on architecture, use cases, IP design, tools, and documentation.

Job Qualifications

BS with 5+ years of exp or MS with 3+ years of exp or PhD in Electrical Engineering or Computer Engineering or related equivalent

• Excellent C/C++ coding skills
• Experience in developing Math functions using Python
• Familiarity with VLIW SIMD vector processor architecture,
• Experience in processor performance and memory modeling
• Experience in creating system designs with compute engine, NOC and DDR/HBM
• Experience in system debug using gdb, Valgrind and other debug tools is required
• Experience in graph programming model, graph optimization techniques will be a plus
• Experience in kernel development using high level synthesis is a plus
• Experience in TensorFlow, PyTorch, Keras is a plus
• Familiarity in Matlab signal processing library and 5G toolbox is a plus
• Strong communication skills

AMD is a US federal government contractor and subcontractor and our employees are subject to any and all federal guidelines by Executive Order or OSHA related to COVID-19 vaccination. If selected to be hired, you may be required to be vaccinated against COVID-19 and submit proof of vaccination or have an approved exemption as required by law.