Atharva Chandwadkar — Associate Consultant

I’m an AI Infrastructure Architect passionate about pushing the limits of AI infrastructure and GPU optimization. My expertise lies in accelerating deep learning and large language models workloads from CUDA kernel tuning and memory optimization to end-to-end infrastructure design for enterprise AI adoption. I have hands on experience across the stack: Low-level performance engineering → CUDA, cuBLAS, cuDNN, TensorRT, memory coalescing, kernel parallelization. Model acceleration → LLM fine-tuning, inference optimization, distributed training with NCCL, multi-GPU orchestration (Run:AI, Slurm). AI infrastructure design → mapping workloads to the right NVIDIA hardware and optimizing deployments with Triton, NIM microservices, and Kubernetes. What excites me most is helping organizations translate cutting-edge GPU technology into real business outcomes, faster insights, lower costs, and scalable AI systems. I thrive at the intersection of deep technical problem-solving and practical enterprise impact, making AI not just possible, but efficient and production-ready. Always eager to collaborate on high-performance AI systems, GPU acceleration, and enterprise AI infrastructure transformation.

Stackforce AI infers this person is a highly skilled AI Infrastructure Architect specializing in enterprise-level AI solutions and GPU optimization.

Location: Chicago, Illinois, United States

Experience: 2 yrs 4 mos