> Markdown version of [/jobs/ext/3575397-senior-software-engineer](https://www.wearedevelopers.com/jobs/ext/3575397-senior-software-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).

---

# Senior Software Engineer

- **Company:** NEURAL SOLUTIONS LLC
- **Location:** Columbia, MD, United States
- **Experience:** Expert
- **Salary:** $204,000.0 - $247,000.0
- **Contract:** Permanent contract
- **Skills:** Artificial Intelligence, Confluence, JIRA, Monitoring of Systems, Tensorflow, Prometheus, Azure Machine Learning, AI Infrastructure, TorchServe, System Availability, Delivery Pipeline, Grafana, Kubernetes, Deployment Automation, Atlassian Tools, Ollama, Triton Inference Server, LiteLLM, Machine Learning Operations, Hardware Infrastructure, VLLM, Docker
- **Published:** October 4, 2026
- **Apply:** https://www.clearancejobs.com/jobs/9214854/senior-software-engineer

## About the Role

* Experience deploying and managing services in on-premises infrastructure environments.
 * Service containerization and orchestration with Docker/Kubernetes in production environments.
 * Experience with observability and monitoring tools such as Prometheus, Grafana, or equivalent platforms.
 * Knowledge of CI/CD pipelines, GitOps workflows.
 * Atlassian Tools (Jira, Confluence).

Nice to Have:

 * Experience with model serving technologies (vLLM, TorchServe, TensorFlow Serving, Triton Inference Server).
 * Knowledge of AI infrastructure tools and frameworks (LiteLLM, Bifrost, Ray, Ollama).

Experience Required: 12 years with Bachelor's degree in a technical discipline or 16 years without degree

## Description

* Deploy and manage containerized AI/ML services using Kubernetes in on-premises environments.
 * Implement observability and monitoring solutions using Prometheus, Grafana, and related tooling to track system health and usage metrics.
 * Build and maintain CI/CD pipelines and infrastructure-as-code to enable reliable, automated deployment of platform services.
 * Design and implement resilient infrastructure patterns to ensure high availability and performance of mission-critical capabilities.
 * Collaborate with stakeholders to translate operational and reliability requirements into platform engineering solutions.