AI Inference Engineer
Evergrid
AI Inference Engineer
Evergrid
Enterprise AI training and inference platform
United States | Hybrid or Remote | Full-time
The role
You'll work directly with Evergrid's customers to architect, build, and deploy high-scale production inference systems on our infrastructure.
You own customer projects end to end, from early exploration to production deployment and monitoring. You take goals that start out unclear and turn them into reliable services you can monitor, with defined quality, latency, and cost targets. This role is hands-on. It combines software development, inference performance engineering, and customer-facing execution. You'll embed with customer engineering teams and work closely with our platform and infrastructure teams.
What you'll own
Production-grade software systems and inference services, built mainly in Python.
Customer engagements end to end: problem framing, evaluation, proof of concept, production deployment, and monitoring.
Direct work with customer engineering teams through sales, implementation, and expansion.
Turning unclear goals into clear technical specs and well-scoped PoCs.
Inference pipelines optimized for latency, throughput, reliability, and cost.
Improvements to Evergrid's inference stack, tooling, and platform.
Customer-facing initiatives, where you act as engineer, technical lead, and the person who drives execution.
Sound tradeoffs under uncertainty that lead to simple, maintainable solutions.
What you bring
A bachelor's, master's, or PhD in Computer Science, Engineering, Mathematics, or a related field, or equivalent practical experience.
3+ years of professional engineering experience.
Experience with SGLang, vLLM, and other inference engines and schedulers.
Strong production software skills, preferably in Python.
Familiarity with the AI/ML lifecycle: model development, deployment, and monitoring.
Clear communication on complex technical topics.
Experience building, deploying, or optimizing AI/ML systems, which we value highly.
Comfort working directly with customers and owning outcomes end to end.
Benefits & Compensation
Compensation: $140,000 - $160,000
Health insurance
Paid time off and paid holidays
Home office stipend
Evergrid provides a cloud platform for enterprise AI training and inference using high-performance GPU infrastructure. It partners with hardware providers like AMD to access GPUs such as MI300X and MI325X, optimizing software, storage, compute, and networking to maximize GPU utilization and ROI for AI workloads. The platform monitors network, cluster, and node utilization and offers autoscaling, with hard multi-tenancy and provisioned networking for data isolation and secure, predictable performance. Its goal is to help large organizations deploy and manage demanding AI models, including frontier-scale models, with scalable, secure, and cost-controlled infrastructure.
Explore more opportunities at Evergrid