About The Position

Fireworks is seeking a Software Engineer focused on Performance Optimization to improve speed and efficiency throughout its AI infrastructure. The role owns performance work across the stack, from low-level GPU kernels to large-scale distributed systems, with a focus on demanding workloads including large language models (LLMs), vision-language models (VLMs), and video models. The engineer will work with research, infrastructure, and systems teams to identify bottlenecks, implement optimizations, and scale production AI systems. This work will affect the speed, scalability, and cost-effectiveness of generative AI models. The position includes optimizing GPU and system performance for training and inference, improving latency, throughput, memory use, and compute efficiency, and building performance benchmarking and monitoring infrastructure. It also involves collaboration on hardware-efficient model architectures, support for mixed precision and quantization, and scaling systems across multiple GPUs and nodes. Example projects include developing GPU kernels, improving LLM sampling and cache efficiency, optimizing model sharding and communication, and diagnosing numerical instabilities at scale.

Requirements

  • Bachelor’s degree in Computer Science, Computer Engineering, Electrical Engineering, or equivalent practical experience.
  • At least 5 years of experience working on performance optimization or high-performance computing systems.
  • Proficiency in CUDA or ROCm and experience with GPU profiling tools such as Nsight, nvprof, or CUPTI.
  • Familiarity with PyTorch and performance-critical model execution.
  • Experience with distributed-system debugging and optimization in multi-GPU environments.
  • Deep understanding of GPU architecture, parallel programming models, and compute kernels.

Nice To Haves

  • Master’s or PhD in Computer Science, Electrical Engineering, or a related field.
  • Experience optimizing large models for training and inference, including LLMs, VLMs, or video models.
  • Knowledge of compiler stacks or ML compilers such as torch.compile, Triton, or XLA.
  • Contributions to open-source ML or HPC infrastructure.
  • Familiarity with cloud-scale AI infrastructure and orchestration tools such as Kubernetes.
  • Background in ML systems engineering or hardware-aware model design.

Responsibilities

  • Optimize system and GPU performance for high-throughput AI workloads across training and inference.
  • Analyze and improve latency, throughput, memory usage, and compute efficiency.
  • Profile system performance to identify and resolve GPU- and kernel-level bottlenecks.
  • Implement low-level optimizations using CUDA, Triton, and other performance tooling.
  • Improve execution speed and resource utilization for large-scale LLM, VLM, and video model workloads.
  • Collaborate with ML researchers to co-design and tune model architectures for hardware efficiency.
  • Improve support for mixed precision, quantization, and model graph optimization.
  • Build and maintain performance benchmarking and monitoring infrastructure.
  • Scale inference and training systems across multi-GPU and multi-node environments.
  • Evaluate and integrate optimizations for emerging hardware accelerators and specialized runtimes.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service