> Markdown version of [/jobs/ext/4629177-ml-infrastructure-engineer](https://www.wearedevelopers.com/jobs/ext/4629177-ml-infrastructure-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).

---

# ML Infrastructure Engineer

- **Company:** Lattice Incorporated
- **Location:** San Francisco, CA, United States
- **Experience:** Experienced
- **Contract:** Permanent contract
- **Skills:** Systems Engineering, Artificial Neural Networks, C++ (Programming Language), Distributed Computing Environment, Python (Programming Language), Machine Learning, Open Source Technology, System Programming, Pytorch, Transfer Learning, Kubernetes, ONNX (Open Neural Network Exchange) Format, Machine Learning Operations, TensorRT, VLLM
- **Published:** November 7, 2026
- **Apply:** https://www.juju.com/job/28_25197_7b823c689267b25207c2d8bf60ccad9e

## About the Role

* 4+ years of experience in ML engineering or infrastructure
 * Strong proficiency in Python and experience with PyTorch or JAX
 * Experience with ML training frameworks and distributed training
 * Familiarity with model serving (TensorRT, ONNX, vLLM)
 * Experience with Kubernetes and container orchestration
 * Understanding of ML fundamentals and neural network architectures, * Experience with LLM fine-tuning and deployment
 * Background in systems programming (C++, Rust)
 * Experience with multi-GPU and multi-node training
 * Contributions to ML open-source projects

## Description

Join our ML Infrastructure team to build the systems that train, deploy, and serve our AI models at scale. You'll work at the intersection of machine learning and systems engineering.

What You Will Do

 * Build and maintain ML training pipelines and infrastructure
 * Design model serving systems for low-latency inference
 * Implement monitoring and observability for ML systems
 * Optimize GPU utilization and reduce training costs
 * Develop tools for model versioning and experiment tracking
 * Collaborate with researchers to productionize new models