> Markdown version of [/jobs/ext/4613136-machine-learning-systems-engineer](https://www.wearedevelopers.com/jobs/ext/4613136-machine-learning-systems-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Machine Learning Systems Engineer

- **Company:** PIVOTS
- **Location:** San Mateo, CA, United States
- **Experience:** Expert
- **Contract:** Permanent contract
- **Skills:** Application Programming Interfaces (APIs), C++ (Programming Language), Encodings, Nvidia CUDA, Linux, General-Purpose Computing on Graphics Processing Units, Python (Programming Language), Software Engineering, Pytorch, Large Language Models, Discretization, Real-time Inference, SGLang, Machine Learning Operations, TensorRT, Mixed Precision, VLLM, CUTLASS
- **Published:** November 7, 2026
- **Apply:** https://www.juju.com/job/28_25197_4fefd5d4e2921acb1511c2bd339c13cd

## About the Role

* 6+ years software engineering, several of them in ML systems, inference, or high-performance GPU computing.
 * Has owned a production serving path end to end, not only benchmarked models.
 * Expert in PyTorch with models shipped to production; knows what will be slow before the profiler runs.
 * Strong CUDA or equivalent GPU depth: memory hierarchy, occupancy, Nsight or equivalent profiling.
 * Rust or C++ alongside Python, Linux performance, production ops; ready to work in Rust daily.
 * Works with researchers: can translate an architecture change into serving work.

## Description

You will own the serving path for Newton and related multimodal models. Much of our inference stack is Rust-native: model nodes in our agent runtime, built on Rust ML stacks (candle, Burn) with custom GPU kernels, plus the routing layer that streams real-time inference to GPU nodes. You will drive GPU utilization, numerical precision, and low-latency serving from the kernel up., * Build and own model nodes in our Rust inference runtime: loading, warmup, batching, streaming, GPU memory pools.

 * Optimize kernels and the GPU path: custom CUDA kernels, mixed precision, quantization, parity against research.
 * Own inference routing and serving: streaming path API to GPU node, request batching, SLO-backed latency and cost.
 * Productionize research checkpoints: export, compilation, quantization, parity evals, and rollout.
 * Build the observability inference needs: latency histograms, GPU metrics, OOM signatures, replayable traces., * Rust ML stacks: candle, Burn, or comparable GPU compute in Rust.
 * Custom kernels and compiler stacks: Triton, CUTLASS, TorchInductor, TensorRT.
 * Quantization and mixed precision in production with a numerical-correctness suite.
 * Multimodal, video, embedding or time-series serving, not only decoder-only chat LLMs.
 * High-performance serving stacks (vLLM, SGLang, TensorRT-LLM): continuous batching, paged KV cache.