> Markdown version of [/jobs/ext/4662057-ml-inference-engineer-model-deployment-java-jvm-google-cloud-platform-hybrid-71513](https://www.wearedevelopers.com/jobs/ext/4662057-ml-inference-engineer-model-deployment-java-jvm-google-cloud-platform-hybrid-71513). 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 Inference Engineer - Model Deployment, Java/JVM, Google Cloud Platform | Hybrid - 71513

- **Company:** PRIMUS Global Services, Inc
- **Location:** Richardson, TX, United States
- **Contract:** Contract
- **Skills:** Java (Programming Language), Distributed Systems, Java Virtual Machine (JVM), Machine Learning, Tensorflow, Data Streaming, Google Cloud, Performance Testing, Pytorch, HybridCloud, Machine Learning Operations
- **Published:** November 10, 2026
- **Apply:** https://www.dice.com/job-detail/5949213c-82bf-4b53-b88f-d651fa2254ce

## About the Role

We have an immediate need for an experienced ML Inference Engineer with strong expertise in Machine Learning (ML) Inference, Model Deployment, Performance Benchmarking, and Quality Validation to design, evaluate, and implement scalable machine learning solutions.

This is a hybrid position based in Richardson, TX 75082, for a candidate with deep experience in ML Inference, Machine Learning Model Deployment, TensorFlow, PyTorch, JAX, Google Cloud Platform (Google Cloud Platform), Model Benchmarking, Performance Testing, Quality Validation, Java/JVM-based Applications, Java Libraries, Distributed Systems, System Design, Streaming Data Architectures, and Hybrid Cloud/On-Premises Environments.

No subcontracting is permitted on this position. Candidates must be willing to work directly on our payroll.