GPU Engineer

MulticoreWare, Inc.; Chennai; On-site; INR 900,000 - 1,800,000; Full time

Job summary

MulticoreWare, Inc. is seeking an experienced GPU Programming Engineer to develop, optimize, and deploy GPU-accelerated solutions for high‑performance deep learning workloads. The role centers on CUDA, HIP, and OpenCL across NVIDIA, AMD, and related platforms.

You will work with system architects and software engineers to port CPU code to GPUs, tune performance, and ensure scalable integration in HPC and AI pipelines.

Qualifications

• 2+ years of hands-on GPU programming experience.
• Strong understanding of GPU architecture, memory hierarchy, shared memory, bank conflicts.
• Proficiency in C/C++ and Linux-based development.
• Familiarity with profiling and tuning tools (Nsight, rocprof, Perfetto).
• Knowledge of DL operators and experience with PyTorch, TensorFlow, or TensorRT is a plus.

Responsibilities

• Develop, optimize, and maintain GPU-accelerated components for deep learning pipelines.
• Analyze and improve GPU kernel performance via profiling, benchmarking, and resource optimization.
• Optimize memory access, compute throughput, and kernel execution for target GPUs.
• Port CPU-based implementations to GPU platforms while ensuring correctness and scalability.
• Collaborate with system architects and engineers to integrate GPU-accelerated solutions.

Skills

GPU programming

CUDA

HIP

OpenCL

C/C++

Linux

Nsight

rocprof

Perfetto

PyTorch

TensorFlow

TensorRT

SIMD

Education

Bachelor's or Master's degree in Computer Science / Electrical Engineering or related field

Tools

Nsight

rocprof

Perfetto

Job description

MulticoreWare is a global software solutions & products company with its HQ in San Jose, CA, USA. With worldwide offices, it serves its clients and partners in North America, EMEA and APAC regions. Started by a group of researchers, MulticoreWare has grown to serve its clients and partners on HPC & Cloud computing, GPUs, Multicore & Multithread CPUS, DSPs, FPGAs and a variety of AI hardware accelerators.

MulticoreWare was founded by a team of researchers that wanted a better way to program for heterogeneous architectures. With the advent of GPUs and the increasing prevalence of multi-core, multi-architecture platforms, our clients were struggling with the difficulties of using these platforms efficiently.

We started as a boot-strapped services company and have since expanded our portfolio to span products and services related to compilers, machine learning, video codecs, image processing and augmented/virtual reality. Our hardware expertise has also expanded with our team; we now employ experts on HPC and Cloud Computing, GPUs, DSPs, FPGAs, and mobile and embedded platforms. We specialize in accelerating software and algorithms, so if your code targets a multi-core, heterogeneous platform, we can help.

Job Description

We are lookingfor an experienced GPU Programming Engineer to develop, optimize, and deployGPU-accelerated solutions for high-performance deep learning workloads. Therole focuses on GPU programming, parallel computing, performance tuning, anddeep learning system integration across platforms such as NVIDIA CUDA, AMDROCm/HIP, and OpenCL.

Responsibilities

• Develop, optimize, and maintain GPU-acceleratedcomponents for deep learning pipelines using CUDA, HIP, or OpenCL.
• Analyze and improve GPU kernel performancethrough profiling, benchmarking, and resource optimization.
• Optimize memory access, compute, throughput, andkernel execution to improve overall system performance on target GPUs.
• Port existing CPU-based implementations to GPUplatforms while ensuring correctness and performance scalability.
• Work closely to system architects, softwareengineers, and domain experts to integrate GPU-accelerated solutions.

Requirements

Education:

• Bachelor's or master's degree in Computer Science, Electrical Engineering, or arelated field.

Technical Skills (Must haves):

• 2+ years of hands-on experience in GPUprogramming, preferably using CUDA, HIP, OpenCL, or similar GPU APIs.
• Strong understanding of GPU architecture, memoryhierarchy, shared memory, bank conflicts, and parallel programming models.
• Proficiency in C/C++ and hands-on experiencedeveloping on Linux-based systems.
• Familiarity with profiling and tuning tools suchas Nsight, rocprof, or Perfetto.

Need to have (Can be bridged):

• Knowledge and experience in SIMD programming.
• Good understanding of neural network (NN)operators and hands-on experience with PyTorch, TensorFlow, or TensorRT.

Good to have (Not essential):

• Exposure to deep learning concepts such asquantization and pruning.
• Experience working with High PerformanceComputing (HPC) systems.

Preferred Qualifications (Optional):

• Additionalexperience in GPU performance engineering, deep learning system optimization,or heterogeneous computing would be advantageous.