AI Inference Engineer - Remote/Hybrid, End-to-End Production

Evergrid; New York (NY); Hybrid; USD 140,000 - 160,000; Full time

Benefits offered by this job

Health insurance

Paid time off and holidays

Home office stipend

Job summary

Evergrid seeks a hands-on engineer to architect, build, and deploy high-scale production inference systems on Evergrid's infrastructure. You will own customer projects end to end, from exploration to production deployment and monitoring, embedding with customer teams and collaborating with platform groups.

Ideal candidates have 3+ years of engineering, strong Python skills, and familiarity with AI/ML lifecycles.

Qualifications

• Requires a degree in CS/Engineering/Math or equivalent 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, monitoring.
• Excellent communication on complex topics.
• Experience building or optimizing AI/ML systems is valued.
• Comfort working directly with customers and owning outcomes end to end.

Responsibilities

• Architect, build, and deploy high-scale production inference systems.
• Own customer projects end to end from exploration to production deployment and monitoring.
• Collaborate with customer engineering teams and Evergrid platform teams.
• Turn unclear goals into well-scoped PoCs and technical specs.
• Optimize inference pipelines for latency, throughput, reliability, and cost.
• Improve Evergrid's inference stack, tooling, and platform.
• Drive customer-facing initiatives and ownership of outcomes.

Skills

3+ years professional software eng

Python production software

Clear communication

AI/ML lifecycle familiarity

Customer-facing experience

Education

Bachelor's, Master's, or PhD in CS/Engineering/Mathematics

Tools

Python

SGLang

vLLM

inference engines

schedulers

Job description

Evergrid seeks a hands-on engineer to architect, build, and deploy high-scale production inference systems on Evergrid's infrastructure. You will own customer projects end to end, from exploration to production deployment and monitoring, embedding with customer teams and collaborating with platform groups.

Ideal candidates have 3+ years of engineering, strong Python skills, and familiarity with AI/ML lifecycles.