Pay
$90K–$150K is typical
The middle half of what similar US postings state. This one doesn’t list pay.
From 23,355 postings in the last year. Stated ranges, not salaries paid.
San Francisco, California, United States
Open 5 months, first seen by us 172 days agoEmployment type in the employer’s posting: FullTimeFrom the employer’s posting
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).
Open 5 monthsWe first saw this posting 172 days ago and it is still up. Roles open this long are often slow to fill or kept open to collect applications.
These dates show when we found the posting. Check the employer’s website to confirm it is still accepting applications.
$90K–$150K is typical
The middle half of what similar US postings state. This one doesn’t list pay.
From 23,355 postings in the last year. Stated ranges, not salaries paid.
Day 172
Up longer than most. Similar jobs usually come down between day 9 and day 60.
Well past Perplexity’s usual: its jobs come down by about day 81.
From 40,906 similar postings that came down, and 6 of Perplexity’s. Coming down is not always a hire.
14 open jobs
Open jobs by the week we first saw them, last 12 weeks.
Add your resume and we’ll mark which of these tools you already use, and point out anything in the posting that could rule you out.
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
- 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.
- 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.
- Profiling and debugging tools: Nsight Compute/Systems, CUDA-GDB, PTX/SASS analysis. - Container orchestration: Kubernetes, GPU scheduling, autoscaling inference workloads. Qualifications
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.
- 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).
Complete your application on jobs.ashbyhq.com. The employer’s form will show what is required.
Already applied? Track this application
Yes. We’ve followed one other Member of Technical Staff (AI Inference Engineer) job there since June 2026. It is still up.
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.
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.
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.
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.
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).
Selected passages from the saved posting. Check the full description for conditions and exceptions.
No pay amount identified in the saved description.
San Francisco, California, United States
Working pattern and location restrictions need checking in the full posting.
No clear work-authorization passage found. Eligibility is unconfirmed.