GPU Computing Engineer / AI Platform Engineer

Tech Mahindra; Bengaluru; Hybrid; INR 4,500,000 - 7,000,000; Full time

Job summary

Tech Mahindra seeks a GPU Computing Engineer in Bengaluru to develop and optimize CUDA-based applications and GPU kernels for AI, simulation, and large-scale workloads. The role focuses on scalable parallel solutions and performance tuning across multi-GPU and distributed environments.

Applicants should have substantial experience with CUDA C/C++, parallel processing, and scheduling algorithms, plus hands-on work with HPC systems. Hybrid work setup in Bengaluru is expected.

Qualifications

• 5-12 years of experience in GPU Computing, HPC, AI Infrastructure, or Performance Engineering.
• Strong understanding of parallel processing and distributed computing concepts.
• Hands-on experience optimizing large-scale compute workloads.
• Proficiency with CUDA C/C++, MPI, NCCL is desirable.

Responsibilities

• Develop and optimize CUDA-based applications and GPU kernels.
• Design scalable parallel computing solutions for compute-intensive workloads.
• Optimize application performance through profiling, benchmarking, and tuning.
• Build and support multi-GPU and distributed computing environments.
• Implement efficient workload scheduling and resource utilization strategies.
• Collaborate with AI/ML, platform, and infrastructure teams.

Skills

CUDA C/C++

Parallel Computing & Multithreading

Python

Performance Optimization

OpenMP

MPI

NCCL

Scheduling Algorithms

Job description

Location: Whitefield, Bengaluru (3 days work from office)

Job Summary

We are looking for a GPU Computing Engineer with strong expertise in CUDA programming, GPU architecture, and parallel computing. The role involves building and optimizing high-performance solutions for AI, simulation, and large-scale computing workloads.

Key Responsibilities

• Develop and optimize CUDA-based applications and GPU kernels.
• Design scalable parallel computing solutions for compute-intensive workloads.
• Optimize application performance through profiling, benchmarking, and tuning.
• Build and support multi-GPU and distributed computing environments.
• Implement efficient workload scheduling and resource utilization strategies.
• Collaborate with AI/ML, platform, and infrastructure teams.

Required Skills

• CUDA C/C++
• Parallel Computing & Multithreading
• Python
• Performance Optimization
• OpenMP, MPI, NCCL
• Scheduling Algorithms

Preferred Skills

Desired Profile

• 5-12 years of experience in GPU Computing, HPC, AI Infrastructure, or Performance Engineering.
• Strong understanding of parallel processing and distributed computing concepts.
• Hands-on experience optimizing large-scale compute workloads.