N

Senior Kernel Engineer (GPU & AI Inference Optimization)

neurospark ai • United States
Visa Sponsorship
Apply Now
AI Summary

Design and optimize high-performance GPU kernels for NeuroSpark’s AI inference platform, improving latency, throughput, and hardware efficiency. Work at the intersection of model architecture, GPU execution, and distributed systems to push performance boundaries across emerging hardware. Hands-on role with full technical ownership, collaborating with cross-functional teams to scale LLM inference at enterprise scale.

Key Highlights
Optimize performance-critical GPU kernels for AI workloads (GEMM, attention, quantization, MoE, etc.) using CUDA, Triton, and low-level GPU techniques
Profile and diagnose bottlenecks in production inference workloads, implementing hardware-aware optimizations for latency, throughput, and memory efficiency
Collaborate with hardware vendors and engineering teams to extend NeuroSpark’s inference stack across heterogeneous accelerators (NVIDIA, AMD, and beyond)

Searching for Development & Programming roles that provide visa sponsorship? Connect with international employers through Development & Programming Jobs with Visa Sponsorship opportunities actively seeking talented professionals.

Key Responsibilities
Design, implement, and optimize high-performance GPU kernels for AI operations (GEMM, attention, normalization, quantization, KV-cache, and MoE workloads)
Profile production inference workloads to identify bottlenecks in compute, memory bandwidth, kernel launch overhead, and synchronization, then optimize using techniques like memory coalescing, shared-memory utilization, tiling, and warp-level programming
Develop and integrate optimized kernels into inference frameworks (PyTorch, Triton, vLLM, SGLang, TensorRT-LLM) while ensuring numerical correctness and production readiness
Extend NeuroSpark’s inference stack across heterogeneous hardware (NVIDIA/AMD GPUs) and emerging AI accelerators, collaborating with hardware vendors and engineering teams
Build and maintain benchmarks, correctness tests, and performance regression tests to validate kernel improvements
Optimize workloads for multi-GPU and distributed environments, improving concurrency, latency, and hardware utilization
Technical Skills Required
CUDA and GPU Programming C++ Performance Optimization (Profiling, Benchmarking, Low-Level Hardware Analysis)

Explore our comprehensive directory of visa sponsorship jobs from employers worldwide who are ready to sponsor talented international professionals.

Benefits & Perks
Equity / stock options
Medical, dental, and vision coverage
Unlimited PTO

Interested in opportunities specifically in United State? Discover our dedicated Visa Sponsorship Jobs in United State page featuring roles from top employers in this location.

Nice to Have
PTX/SASS, CUTLASS, or CuTe for low-level GPU programming
Experience with inference frameworks (vLLM, SGLang, TensorRT-LLM, FlashInfer)
FlashAttention or fused attention kernel implementation
ROCm/HIP for AMD GPU optimization
ML compiler/runtime systems (torch.compile, XLA, MLIR, TVM)
Distributed training/inference (tensor/pipeline/expert parallelism)
Open-source contributions in GPU kernels, ML systems, or inference engines

Job Description

NeuroSpark builds and operates a high-performance AI inference platform that helps enterprises run large language models faster, cheaper, and at scale. Inference infrastructure is the foundation the entire AI application layer runs on — every AI product ultimately depends on how fast, how reliably, and how affordably models can serve their users. Our vision is to make that layer so efficient that compute is never the reason a good AI product fails.NeuroSpark Inc operates an enterprise AI inference platform providing high-throughput, low-latency access to large language models across a distributed, heterogeneous compute fleet.As a
Want the full job description? Read the complete details on LinkedIn, the original posting.
Continue on LinkedIn

This is a short excerpt. All rights to the full description belong to its original publisher.

Ready to apply?

Apply Now
See Jaabz jobs first on Google 1 tap · free · in AI Overviews Jaabz is on your Google Manage Preferred Sources
Job Overview
Posted Nov 04, 2026
Employment Full-time
Experience Not Applicable
Location United States
Category Programming
Company neurospark ai
Keep exploring

Similar Jobs

Explore other opportunities that match your interests

Visas, Work Permits & Legal Insights

Stay informed about visa types, work permits, and immigration updates for international professionals.

Browse all articles

Subscribe to our newsletter

New visa sponsorship, relocation and remote tech jobs, delivered to your inbox.