We are looking
for a talented engineer to implement and optimize machine learning, computer
vision, and numeric libraries for target hardware architectures, including
CPUs, GPUs, DSPs, and other accelerators. Your expertise will be instrumental
in enabling efficient and high-performance execution of algorithms on these
hardware platforms.
Responsibilities:
• Implement and optimize machine learning, computer
vision, and numeric libraries for target hardware architectures, including
CPUs, GPUs, DSPs, and other accelerators.
• Work closely with software and hardware engineers
to ensure optimal performance on target platforms.
• Implement low-level optimizations, including
algorithmic modifications, parallelization, vectorization, and memory access
optimizations, to fully leverage the capabilities of the target hardware
architectures.
• Work with customers to understand their
requirements and implement libraries to meet their needs.
• Develop performance benchmarks and conduct
performance analysis to ensure the optimized libraries meet the required
performance targets.
• Stay current with the latest advancements in
machine learning, computer vision, and high-performance computing.
Requirements
Education:
BTech/BE/MTech/ME/MS/PhD
in CSE/IT/ECE.
Technical Skills (Must haves):
• Proficient in programming languages such as
C/C++, CUDA, OpenCL, or other relevant languages for hardware optimization.
• Hands-on experience with hardware architectures,
including CPUs, GPUs, DSPs, and accelerators, and familiarity with their
programming models and optimization techniques.
• Knowledge of parallel computing, SIMD
instructions, memory hierarchies, and cache optimization techniques.
• Experience with performance analysis tools and
methodologies for profiling and optimization.
Need to have (Can be bridged):
• More than 4 years of experience in Algorithm
Development, Porting, Optimization & Testing.
• Strong problem-solving skills and ability to work
independently or within a team.
Good to have (Not essential):
Knowledge of
deep learning frameworks and techniques.
Preferred Qualifications (Optional):
Hands-on
experience optimizing algorithms and libraries for heterogeneous hardware
platforms and high-performance computing environments.
Skills Required
- BTech, BE, MTech, ME, MS, or PhD in Computer Science, Information Technology, Electronics, Electronics and Communication Engineering, or a related field
- More than 4 years of experience in algorithm development, porting, optimization, and testing
- At least 4 years of experience in algorithm development or software optimization
- Strong programming skills in C or C++
- Experience with CUDA, OpenCL, or similar parallel programming technologies
- Experience working with CPUs, GPUs, DSPs, FPGAs, or other accelerators
- Hands-on FPGA development experience using VHDL, Verilog, HLS, Xilinx Vivado, Xilinx Vitis, Intel Quartus, or similar tools
- Knowledge of parallel computing, SIMD instructions, memory hierarchies, cache optimization, and performance optimization
- Experience with performance analysis, profiling, benchmarking, and optimization methodologies
- Strong problem-solving, debugging, independent work, and teamwork skills
- Knowledge of deep learning frameworks and techniques
- Experience with TensorFlow, PyTorch, or other AI/ML frameworks
- Knowledge of LLVM, MLIR, or TVM
- Experience in embedded systems or AI acceleration
What We Do
MulticoreWare delivers software IP Solutions and Engineering Services serving a wide group of customers with Compilers & Toolchains, Libraries for SDK, Video codec and AI analytics solutions using various vision & non-vision (Radar, LiDAR, IMU, GPS, etc.) sensors on various heterogenous computing platforms. Our solutions are used in Automotive (ADAS/AD), Surveillance, Defence, Medical Imaging, IoT, Retail, Logistics, Industrial, Robotics, Smart City. MulticoreWare’s industry-leading video codec products (x266™/x265/Ultraziq) have been deployed in live streaming or VOD services across many broadcast customers. FOLLOW US ON SOCIAL MEDIA Youtube: https://www.youtube.com/channel/Multicoreware Twitter: https://twitter.com/MulticoreWare Facebook: https://www.facebook.com/multicoreware Instagram: https://www.instagram.com/multicoreware.inc/
