Exciting chance for a Software Engineer focused on AI inference systems to drive optimizations and improve efficiency for large-scale models. Utilize your expertise in GPU technologies!We are looking for skilled engineers who will architect and optimize high-performance AI inference software. This role involves collaborating with teams to enhance ML frameworks like PyTorch and contribute to significant research advancements. Your innovative solutions will greatly impact the efficiency of inference processing and model serving.Key Responsibilities:
- Contribute to the newest models with advanced features
- Profile and enhance framework performance with optimizations
- Architect runtime solutions and conduct research




- Develop GPU kernels using optimization techniques
- Benchmark inference performance with cutting-edge methodologiesRequirements:
- Bachelor’s, Master’s, or PhD in Computer Science or Engineering
- 5+ years of experience in software engineering or research
- Expertise in Python and one of C/C++, Go, or Rust
- Knowledge of GPU performance and ML frameworks
- Strong problem-solving and communication abilitiesTransform the future of AI with performance innovations and groundbreaking research at our company.#J-18808-Ljbffr

📌 Software Engineer For Ai Inference Systems (Toronto)
🏢 United States Digital Space
📍 Toronto