Member of Technical Staff (Performance Optimization)

Fireworks AI; United States; On-site; USD 150,000 - 260,000; Full time

Job summary

Fireworks AI is seeking a Software Engineer focused on Performance Optimization to push speed and efficiency across our AI infrastructure. You will own optimization at every layer, from GPU kernels to large-scale distributed systems.

Collaborating with research, infrastructure, and systems teams, you will target bottlenecks in LLMs, VLMs, and video models, improve latency and memory use, and drive CUDA, Triton, and PyTorch optimizations for production workloads.

Qualifications

• Bachelor's degree in CS/CE/EE or equivalent practical experience.
• 5+ years of experience in performance optimization or HPC.
• Experience optimizing large models for training and inference (LLMs, VLMs, or video models).
• Proficiency in CUDA or ROCm and GPU profiling tools (Nsight, nvprof, CUPTI).
• Familiarity with PyTorch and performance-critical model execution.
• Experience with distributed systems debugging and multi-GPU optimization.
• Contributions to open-source ML or HPC infrastructure.
• Knowledge of compiler stacks or ML compilers (e.g., torch.compile, Triton, XLA).
• Familiarity with cloud-scale AI infrastructure and orchestration tools (Kubernetes).
• Background in ML systems engineering or hardware-aware model design.

Responsibilities

• Analyze and optimize performance across GPU kernels and distributed systems.
• Profile bottlenecks and implement low-level optimizations using CUDA, Triton, and related tools.
• Collaborate with ML researchers to co-design hardware-efficient model architectures.
• Scale inference and training across multi-GPU, multi-node environments.
• Build and maintain performance benchmarking and monitoring infrastructure.

Skills

Performance optimization

GPU kernel optimization

CUDA

Triton

PyTorch

Distributed systems

Profiling

Load balancing

Hardware-aware optimization

High-performance computing

Education

Bachelor's degree in Computer Science/Engineering

Master's or PhD in Computer Science/Electrical Engineering

Tools

CUDA

ROCm

Nsight

nvprof

CUPTI

PyTorch

Triton

XLA

Kubernetes

Job description

• We're looking for a Software Engineer focused on Performance Optimization to help push the boundaries of speed and efficiency across our AI infrastructure
• In this role, you'll take ownership of optimizing performance at every layer of the stack—from low-level GPU kernels to large-scale distributed systems
• A key focus will be maximizing the performance of our most demanding workloads, including large language models (LLMs), vision-language models (VLMs), and next-generation video models
• You'll work closely with teams across research, infrastructure, and systems to identify performance bottlenecks, implement cutting-edge optimizations, and scale our AI systems to meet the demands of real-world production use cases
• Your work will directly impact the speed, scalability, and cost-effectiveness of some of the most advanced generative AI models in the world
• 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 detect and resolve GPU- and kernel-level bottlenecks
• Implement low-level optimizations using CUDA, Triton, and other performance tooling
• Drive improvements in execution speed and resource utilization for large-scale model workloads (LLMs, VLMs, and video models)
• 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, multi-node environments
• Evaluate and integrate optimizations for emerging hardware accelerators and specialized runtimes
• Example projects:
• Implement fully asynchronous low-latency sampling for large language models integrated with structured outputs
• Implement GPU kernels for the new low-precision scheme and run experiments to find optimal speed-quality tradeoff
• Build a distributed router with a custom load-balancing algorithm to optimize LLM cache efficiency
• Define metrics and build harness for finding optimal performance configuration (e.g. sharding, precision) for a given class of model
• Determine and implement in PyTorch an optimal sharding scheme for a novel attention variant
• Optimize communication patterns in RDMA networks (Infiniband, RoCE)
• Debug numerical instabilities for a given model for a small portion of requests when deployed at scale
• Experience with distributed system debugging and optimization in multi-GPU environments
• Deep understanding of GPU architecture, parallel programming models, and compute kernels
• Proficiency in CUDA or ROCm and experience with GPU profiling tools (e.g., Nsight, nvprof, CUPTI)
• Familiarity with PyTorch and performance-critical model execution
• Bachelor's degree in Computer Science, Computer Engineering, Electrical Engineering, or equivalent practical experience
• 5+ years of experience working on performance optimization or high-performance computing systems
• Experience optimizing large models for training and inference (LLMs, VLMs, or video models)
• Master's or PhD in Computer Science, Electrical Engineering, or a related field
• Contributions to open-source ML or HPC infrastructure
• Knowledge of compiler stacks or ML compilers (e.g., torch.compile, Triton, XLA)
• Familiarity with cloud-scale AI infrastructure and orchestration tools (e.g., Kubernetes)
• Background in ML systems engineering or hardware-aware model design