Member of Technical Staff (AI Inference Engineer)

Perplexity; Greater London; On-site; GBP 70,000 - 95,000; Full time

Benefits offered by this job

Equity options

Competitive compensation

Job summary

A technology company specializing in AI is looking for an AI Inference Engineer to join their team. The ideal candidate should have experience with GPU programming and modern LLM architectures. Responsibilities include developing Rust-based inference servers and optimizing performance. The role requires proficiency in CUDA and familiarity with deep learning frameworks. Competitive compensation includes equity options, with the final offer depending on experience and expertise.

Qualifications

• Deep experience with GPU programming and performance work (CUDA, Triton, etc.).
• Experience with ML inference or high-performance systems.
• Familiarity with at least one deep learning framework (PyTorch, JAX, TensorFlow).

Responsibilities

• Support transformer-based retrieval and generation models in inference infrastructure.
• Develop internal Rust-based inference server to manage traffic.
• Build dashboards and alerts for reliability and observability.

Skills

Deep experience with GPU programming

Understanding of modern LLM architectures

Building production distributed systems

Comfortable with Rust, Python, CUDA

Self-directed in fast-paced environments

Education

3+ years of professional software engineering

Tools

CUDA

Kubernetes

PyTorch

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.