Senior Staff ML Engineer — Real-Time Inference at Scale

HellaGoodAudio; United States; Remote; USD 188,000 - 269,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

Inworld is seeking engineers to advance real-time AI inference for consumer apps. You will contribute to scalable serving stacks, optimize latency and throughput, and own end-to-end model deployment from research to production.

Ideal candidates have PhDs or equivalent hands-on expertise in backend/ML systems, with experience in Kubernetes, Ray, CUDA and related tools. Relocation support may be available for global candidates.

Qualifications

• Experience delivering reliable, scalable inference systems.
• Knowledge of modern serving frameworks and acceleration techniques.
• Proven ability to take models from research to production.
• PhD or comparable practical experience in backend/ML systems.

Responsibilities

• Own deployment of model serving stacks from research to production.
• Optimize latency, throughput and reliability for real-time workloads.
• Collaborate on distributed, multi-GPU/multi-node inference platforms.

Skills

Inference optimization

Model acceleration

High-performance systems

Distributed systems & scaling

Open-source contributions

Full-cycle ownership

Backend systems

Education

PhD in CS, Physics, Math or equivalent

Tools

Kubernetes

Ray

vLLM

CUDA

Job description

Inworld is seeking engineers to advance real-time AI inference for consumer apps. You will contribute to scalable serving stacks, optimize latency and throughput, and own end-to-end model deployment from research to production.

Ideal candidates have PhDs or equivalent hands-on expertise in backend/ML systems, with experience in Kubernetes, Ray, CUDA and related tools. Relocation support may be available for global candidates.