Dreamwork is seeking an AI Inference Engineer to join our expanding team. We build and run the inference engine powering Perplexity queries, deploying diverse model architectures with tight latency and cost budgets. Our stack includes Rust, Python, CUDA, and CuTe DSL.
You will work on supporting new models, migrating CUDA kernels to CuTe DSL, and building a Rust-based serving runtime. The role emphasizes performance, reliability, and end-to-end ownership in a fast-moving environment.
AI Inference Engineer: GPU, Rust & High-Performance employer: Dreamwork
Dreamwork provides a supportive work environment that emphasizes professional growth and innovation. Employees are part of a culture that values operational excellence and continuous improvement, making it an attractive place for those looking to advance their careers in technology services.