Machine Learning Engineer - Inference / Serving

Yobi(3 months ago)

HybridFull TimeSenior$157,448 - $211,361 (estimated)Engineering & Science

About this role

The Machine Learning Engineer - Inference / Serving at Yobi is responsible for designing, optimizing, and operating real-time systems that deploy Behavioral AI models for open-web and connected TV products. This role requires expertise in model deployment, low-latency architecture, and high-performance coding in languages such as Go, Rust, C++, or Java. The engineer will ensure models are effectively packaged, versioned, and monitored to maintain performance and reliability in a production environment, contributing to the company's vision of ethical data utilization.

View Original Listing

Required Skills

Machine Learning
Model Deployment
Low-Latency Inference
Systems Fluency
High-Performance Code
Operational Maturity
Infrastructure Intuition
Applied ML Understanding
Production Environment
Model Integration

+7 more

About Yobi

yobi.ai

Yobi is an AI-driven platform that aims to democratize the use of artificial intelligence in various industries by leveraging behavioral machine learning models. With a focus on predictive consumer behavior, Yobi integrates extensive data partnerships to enhance customer experiences through hyper-personalization and marketing optimization. The platform provides solutions for machine learning, media performance, and site personalization, helping businesses understand and anticipate consumer demands effectively. Yobi's innovative framework empowers organizations to create data-driven strategies that drive growth and improve operational efficiency.