Integrate transformer-based retrieval, text-generation, and multimodal models into inference infrastructure, including weight loading, request scheduling, KV-cache management, and API Gateway support.
Port CUDA kernels to CuTe DSL and develop a Rust-based inference server.
Profile and optimize performance across network ingress, continuous batching, and GPU kernel interleaving.
Build reliability dashboards, alerts, and automated remediation, and respond to production incidents.
Summarised from the posting by AI and can be wrong. The full description is the source.
Requirements
Experience
3+ years of professional software engineering experience with meaningful work on ML inference or high-performance systems
Deep experience with GPU programming and performance work using CUDA, Triton, CUTLASS, or similar
Experience bringing modern LLM architectures up reliably in a production environment
Experience building and operating production distributed systems under real load
Deep systems programming experience (preferred)
Experience with ML compilers and framework internals, including PyTorch internals, torch.compile, or custom operators (preferred)
Experience with distributed GPU communication, including NCCL, NVLink, InfiniBand, RDMA libraries, or model/tensor parallelism (preferred)
Experience with low-precision inference, including INT8/FP8/FP4 quantization or mixed-precision serving (preferred)
Experience with Nsight Compute/Systems, CUDA-GDB, or PTX/SASS analysis (preferred)
Experience with Kubernetes, GPU scheduling, or autoscaling inference workloads (preferred)
Skills
Familiarity with at least one deep learning framework (PyTorch, JAX, or TensorFlow)
Understanding of GPU architectures, including memory hierarchy, warp scheduling, and tensor cores
Understanding of common LLM architectures and inference optimization techniques
Comfort working across Rust, Python, and CUDA/CuTe DSL
Your match
Sign in and add your resume to see which of this job's requirements it shows.
Saved to your account, encrypted. The AI that reads it doesn't keep it or train on it.
Full job description
From Perplexity’s careers site
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.
Show full descriptionShow less
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.
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).