Senior AI Infra Engineer: Scale & Secure ML on GPUs

Dover; Santa Clara, Northern (CA, KY); Hybrid; USD 150,000 - 170,000; Full time

Benefits offered by this job

Unlimited PTO

Generous parental leave

Stock Purchase Program (ESPP)

Annual bonus program

Medical, Dental and Vision coverage

Mental health support

Job summary

Dover is seeking a Software Engineer specialized in AI/ML applications to independently drive end-to-end lifecycle management of AI-powered systems, blending advanced AI development with robust software engineering and automation.

You will deploy and scale open-source models on distributed GPU infrastructure, design automated testing frameworks, and implement secure CI/CD pipelines that ensure quality on every merge.

Qualifications

• 6+ years of production-grade, asynchronous Python development with clean architecture.

Responsibilities

• Architect and scale AI infrastructure across multi-node clusters using Kubernetes, Ray, or Slurm.
• Design, evaluate, and deploy production-grade AI models and agents with benchmarks.
• Conduct comprehensive model benchmarks and dashboards to communicate performance to stakeholders.
• Develop extensive automated test suites for end-to-end applications and stochastic AI outputs.
• Automate DevSecOps with vulnerability scanning in Merge Requests and fast remediation pipelines.
• Own features end-to-end from ideation to production, including repository synchronization and OSS interactions.

Skills

Python programming

AI systems design

Data analysis (pandas/NumPy)

GitLab pipelines

PyTest testing

Advanced Git workflows

Education

Bachelor's or Master's in CS/Engineering

Tools

Kubernetes

Ray

Slurm

LangChain

Hugging Face

MLOps

vLLM

SGLang

GitLab

PyTest

Job description

Dover is seeking a Software Engineer specialized in AI/ML applications to independently drive end-to-end lifecycle management of AI-powered systems, blending advanced AI development with robust software engineering and automation.

You will deploy and scale open-source models on distributed GPU infrastructure, design automated testing frameworks, and implement secure CI/CD pipelines that ensure quality on every merge.