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.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
Job Type
Full-time
Career Level
Senior