Senior Lead Software Engineer- Inference Platform Engineer

What you'll do

• Architect, deploy, monitor, and optimize cloud platforms and resources for AI/ML performance and cost efficiency.
• Build CI/CD, automation, and infrastructure-as-code for ML deployment and operations; partner with AI teams to translate compute needs into infrastructure.
• Guide engineering teams and promote secure, validated AI-assisted development practices across the software delivery lifecycle.

What they ask for

• Formal training or certification in software engineering concepts and 5+ years of applied experience.
• Hands-on experience in system design, application development, testing, and operational stability; experience with Infrastructure as Code.
• Strong experience with Kubernetes and Docker, including cluster operations and production troubleshooting.
• Proficiency in at least one of Python, Go, Java, or C#; knowledge of cloud delivery and deployment models, cloud architecture, and foundational machine learning concepts.

Nice to have

• Foundational understanding of NVIDIA GPU infrastructure software (e.g., DCGM, BCM, Dynamo Inference); observability tools such as Prometheus and Grafana; or ML Ops tooling including MLflow.
• Experience building and scaling high-performance LLM inference platforms using vLLM and GPU/CPU serving optimization.

Pay

USD $175,750.00-$260,000.00 base salary

Tools

Kubernetes, Docker, Python, Go, Java, C#, Prometheus, Grafana

AI focus

Architect and operate AI/ML and LLM inference infrastructure; apply and govern approved AI-assisted engineering tools, validating outputs for correctness, performance, security, and responsible use.