Perplexity

AI Inference Engineer responsible for building and running the inference engine for Perplexity's models, focusing on performance, reliability, and cost-efficiency across various model architectures and GPU hardware. The role involves migrating CUDA kernels to CuTe DSL, developing a Rust-based serving runtime, and optimizing performance from network ingress to GPU kernels.

AI Infrastructure Engineer responsible for building, deploying, and optimizing large-scale AI training and inference clusters using Kubernetes and Slurm on AWS. The role involves managing HPC environments, developing orchestration systems, implementing resource scheduling, and building monitoring solutions for ML workloads.

AI Inference Engineer responsible for building and running the inference engine for Perplexity's models, focusing on performance, latency, and cost optimization across various model architectures. The role involves supporting transformer-based models, migrating GPU kernels, developing a Rust-native serving runtime, and ensuring reliability and observability of the inference infrastructure.

Engineering Site Lead for Perplexity in London, responsible for establishing and scaling the office, building and managing infrastructure and AI infrastructure teams, and driving technical excellence in AI systems. The role involves direct people management, setting technical direction, and ensuring robust systems for AI/ML workloads.

Internship program focused on improving the AI inference engine and serving stack for Perplexity products, optimizing latency and throughput on large GPU clusters, and supporting new models and inference optimizations.