Member of Technical Staff (AI Inference Engineer)

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

We are looking for an AI Inference Engineer to join our growing team. We build and run the inference engine behind every Perplexity query and deploy dozens of model architectures at scale with tight latency and cost budgets. Our stack is Rust, Python, CUDA, and CuTe DSL.

Responsibilities

• New models support. Support transformer-based retrieval, text-generation, and multimodal models in our inference infrastructure, from weight loading, request scheduling and KV-cache management to support in API Gateway.
• GPU kernels migration to CuTe DSL. Port our in-house CUDA kernels to NVIDIA's CuTe DSL so they run on GB200 today and are portable to Vera Rubin racks tomorrow.
• Rust-native serving runtime. Develop our internal Rust-based inference server to solve all Python pains and keep up with rapidly growing traffic.
• Performance optimisation. Profile and fix bottlenecks from network ingress through continuous batching and GPU kernels interleaving.
• Reliability and observability. Build dashboards, alerts, and automated remediation so we catch regressions before users do. Respond to and learn from production incidents.

Who We're Looking For

• Deep experience with GPU programming and performance work (CUDA, Triton, CUTLASS, or similar). Any other deep systems programming experience is a plus.
• You understand modern LLM architectures and are able to bring them up reliably in a production environment.
• You've built and operated production distributed systems under real load - ideally performance-critical ones.
• Comfortable working across languages and layers: Rust for the serving runtime, Python for model code, CUDA/CuteDSL for kernels.
• You own problems end-to-end. You can read a research paper on Monday, write a kernel on Wednesday, and debug a production incident on Friday.Self-directed. You do well in fast-moving environments where the path forward isn't laid out for you.

Nice-to-have

• ML compilers and framework internals: PyTorch internals, torch.compile, custom operators.
• Distributed GPU communication: NCCL, NVLink, InfiniBand, RDMA libraries, model/tensor parallelism.
• Low-precision inference: INT8/FP8/FP4 quantization, mixed-precision serving.
• Profiling and debugging tools: Nsight Compute/Systems, CUDA-GDB, PTX/SASS analysis.
• Container orchestration: Kubernetes, GPU scheduling, autoscaling inference workloads.

Qualifications

• 3+ years of professional software engineering experience with meaningful work on ML inference or high-performance systems.
• Familiarity with at least one deep learning framework (PyTorch, JAX, TensorFlow).
• Understanding of GPU architectures (memory hierarchy, warp scheduling, tensor cores).
• Understanding of common LLM architectures and inference optimization techniques (e.g. quantization, speculative decoding, prefill-decode disaggregation).

Final offer amounts are determined by multiple factors including experience and expertise.

Equity: In addition to the base salary, equity may be part of the total compensation package.