> Markdown version of [/jobs/ext/3846765-machine-learning-systems-engineer-inference-in-new-york](https://www.wearedevelopers.com/jobs/ext/3846765-machine-learning-systems-engineer-inference-in-new-york). 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 (Inference) in New York

- **Company:** Energy Jobline
- **Location:** New York, NY, United States
- **Experience:** Expert
- **Contract:** Permanent contract
- **Skills:** C++ (Programming Language), Nvidia CUDA, Distributed Computing Environment, Distributed Systems, Python (Programming Language), Machine Learning, Open Source Technology, Tensorflow, Pytorch, cuDNN, Gpu Programming, Low Latency, Machine Learning Operations, TensorRT
- **Published:** October 20, 2026
- **Apply:** https://www.energyjobline.com/job/machine-learning-systems-engineer-inference-new-york-32010950

## About the Role

* 5+ years of experience in machine learning with a focus on training or inference systems
\n

 * Hands-on experience with real-time, low-latency ML pipelines in high-performance
\n

 * environments is a strong plus
\n

 * Strong engineering skills, including Python, CUDA, or C++
\n

 * Knowledge of machine learning frameworks such as PyTorch, TensorFlow, or JAX
\n

 * Proficiency in GPU programming for training and inference acceleration (e.g., CuDNN, TensorRT)
\n

 * Experience with distributed training for scaling ML workloads (e.g., Horovod, NCCL)
\n

 * Exposure to cloud platforms and orchestration tools
\n

 * A track record of contributing to open-source projects in machine learning, data science, or distributed systems is a plus
\n