AI Inference Engineer (Staff) - GPU ML Systems + Equity

Perplexity; Greater London; On-site; GBP 80,000 - 120,000; Full time

Benefits offered by this job

Equity

Job summary

Perplexity is hiring an AI Inference Engineer to scale our inference engine behind every query. You will work on loading weights, scheduling requests, and managing KV-cache, with a stack of Rust, Python, CUDA, and CuTe DSL.

You will port CUDA kernels to CuTe DSL, optimize performance under tight latency and cost budgets, and build a robust Rust-based serving runtime to support growing traffic and model architectures.

Qualifications

• 3+ years of professional software engineering experience in ML inference or high-performance systems.
• Familiarity with at least one deep learning framework (PyTorch, JAX, TensorFlow).
• Understanding of GPU architectures and memory hierarchy.
• Experience building production distributed systems under real load.
• Comfortable working across languages: Rust for serving, Python for model code.

Responsibilities

• Support new models including transformer-based retrieval, text generation, and multimodal models in inference infrastructure.
• Migrate GPU kernels to CuTe DSL to run on GB200 today and Vera Rubin racks tomorrow.
• Develop a Rust-based internal inference server to handle increasing traffic.
• Profile and fix bottlenecks from network ingress through batching and GPU interleaving.
• Build dashboards, alerts, and automated remediation to catch production regressions.

Skills

GPU programming

Performance optimisation

Distributed systems

Rust

Python

CUDA

Tools

CuTe DSL

CUDA kernels

Rust

Python

Triton

Job description

Perplexity is hiring an AI Inference Engineer to scale our inference engine behind every query. You will work on loading weights, scheduling requests, and managing KV-cache, with a stack of Rust, Python, CUDA, and CuTe DSL.

You will port CUDA kernels to CuTe DSL, optimize performance under tight latency and cost budgets, and build a robust Rust-based serving runtime to support growing traffic and model architectures.