Member of Technical Staff (AI Inference Engineer)
Perplexity3 months ago
London, United KingdomMid Level / Senior
H1B Sponsor
Responsibilities
- Support transformer-based retrieval, text-generation, and multimodal models in the inference infrastructure.
- Port in-house CUDA kernels to NVIDIA's CuTe DSL for improved portability.
- Develop an internal Rust-based inference server to enhance performance.
- Profile and fix performance bottlenecks across the system.
- Build dashboards and alerts for system reliability and observability.
Requirements
- 3+ years of professional software engineering experience in ML inference or high-performance systems.
- Deep experience with GPU programming (CUDA, Triton, or similar).
- Familiarity with at least one deep learning framework (PyTorch, JAX, TensorFlow).
- Understanding of GPU architectures and common LLM architectures.
- Ability to work across languages and layers, including Rust, Python, and CUDA.
Benefits
- Equity may be part of the total compensation package.