Staff Technical Program Manager, Deployments

United States | Remote | Full-time

The role

You’ll get Evergrid’s customers live. You’ll lead deployments of high-scale production inference systems on our infrastructure, from technical kickoff through launch and into steady-state operations.

You own each deployment end to end. You take customer requirements that start out unclear, turn them into a concrete plan, and drive it to production with defined quality, latency, and cost targets. This role is hands-on: part program lead, part deployment engineer. You’ll embed with customer engineering teams, work closely with our platform and infrastructure teams, and be the person customers trust to get them to production on schedule.

What you’ll own

• Customer deployments end to end, from technical kickoff to production launch, with clear milestones, owners, and go-live criteria.

• Deployment plans that turn unclear customer requirements into clear technical specs, scoped work, and a path to production.

• Day-to-day technical leadership with customer engineering teams through integration, testing, cutover, and launch.

• Production inference services that meet agreed targets for latency, throughput, reliability, and cost.

• Coordination across Evergrid’s platform and infrastructure teams so capacity, networking, and tooling are ready when customers need them.

• Early risk spotting and sound tradeoffs under pressure that keep launches on schedule.

• Monitoring and stabilizing deployments after go-live, through handoff to steady-state operations.

• Repeatable deployment playbooks and improvements to Evergrid’s inference stack, built from what each launch teaches us.

What you bring

• 5+ years of experience taking complex technical deployments from kickoff to production, ideally with enterprise customers.

• A track record of driving programs to hard deadlines across multiple teams, both inside and outside your company.

• Strong production software skills, preferably in Python, and willingness to get hands-on when a deployment needs it.

• Experience with SGLang, vLLM, and other inference engines and schedulers.

• Working knowledge of the infrastructure inference runs on, such as GPU clusters, orchestration, networking, and observability.

• Clear communication on complex technical topics, with engineers and executives alike.

• Comfort working directly with customers and owning outcomes end to end.

• A bachelor’s, master’s, or PhD in Computer Science, Engineering, Mathematics, or a related field, or equivalent practical experience.

Nice to have

• Experience building, deploying, or optimizing AI/ML systems in production.

Benefits & Compensation

• Compensation: $180,000 – $225,000

• Health insurance

• Paid time off and paid holidays

• Home office stipend