Member of Technical Staff (AI Inference Engineer)
Perplexity7 months ago
London, United KingdomMid Level
Responsibilities
- Support new transformer-based retrieval, text-generation, and multimodal models across weight loading, request scheduling, KV-cache management, and API Gateway support.
- Port in-house CUDA kernels to NVIDIA’s CuTe DSL for current and future GPU platforms.
- Develop the internal Rust-based inference serving runtime.
- Profile and optimize performance from network ingress through continuous batching and GPU kernel execution.
- Build dashboards, alerts, and automated remediation for reliability and regression detection.
- Respond to production incidents and apply operational learnings.
Requirements
- 3+ years of professional software engineering experience with meaningful work in ML inference or high-performance systems.
- Deep experience with GPU programming and performance optimization, such as CUDA, Triton, or CUTLASS.
- Experience with modern LLM architectures and deploying them reliably in production.
- Experience building and operating production distributed systems under real load, ideally performance-critical systems.
- Ability to work across Rust, Python, and CUDA/CuTe DSL.
- Familiarity with at least one deep learning framework: PyTorch, JAX, or TensorFlow.
- Understanding of GPU architectures, including memory hierarchy, warp scheduling, and tensor cores.
- Understanding of LLM architectures and inference optimization techniques such as quantization, speculative decoding, and prefill-decode disaggregation.
- Preferred experience with PyTorch internals, torch.compile, custom operators, NCCL, NVLink, InfiniBand, RDMA libraries, model or tensor parallelism, low-precision inference, Nsight tools, CUDA-GDB, PTX/SASS analysis, Kubernetes, GPU scheduling, or autoscaling inference workloads.
Benefits
- Equity may be included in addition to the base salary as part of the total compensation package.
Tech Stack
Categories
About Perplexity
Perplexity builds an AI-powered answer engine for web and mobile and an enterprise product, Perplexity Computer, for AI-driven workflows across tools and apps. The company monetizes through individual subscriptions (Perplexity Pro) and enterprise plans. Founded in 2022 and headquartered in San Francisco, it operates as a privately held company.