Member of Technical Staff (AI Inference Engineer)

Perplexity; New York (NY); On-site; USD 220,000 - 485,000; Full time

Job summary

Perplexity in New York is seeking an experienced engineer to join our team and own ML inference workloads, building a Rust/Python-based serving runtime and CUDA kernel work that scales to production. You will work with transformer-based models, enabling efficient weight loading, scheduling, and KV-cache management in our in-house infrastructure.

You will read research papers, implement kernels, and diagnose production incidents in a fast-moving environment, collaborating across languages and

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).

Responsibilities

• New models support for transformer-based retrieval, text-generation, and multimodal models in the inference infrastructure.
• Port CUDA kernels to CuTe DSL and migrate GPU kernels for portability.
• Develop a Rust-native serving runtime to handle growing traffic and reduce Python pains.
• Profile and optimize performance across network, batching, and GPU kernel interleaving.
• Build dashboards, alerts, and automated remediation to catch regressions.

Skills

ML inference

High-performance systems

Distributed systems

Rust

Python

CUDA

Tools

PyTorch

JAX

TensorFlow

Job description

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 - and we need another engineer to join us.

What you will work on

Examples Of Real Work The Team Does

• 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 kernel 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.

Good if you touched any of

• 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).

Compensation Range: $220K - $485K