Real-Time ML Inference Engineer — Personalization Systems

Aimlroles; New York (NY); Remote; USD 180,000 - 275,000; Full time

Benefits offered by this job

Competitive base salary

Equity & financial upside

Annual bonus target

Health, Dental, Vision

Unlimited PTO

401k with company match

Generous parental leave

Job summary

Yobi is seeking a Machine Learning Engineer focused on Inference and Serving. You will design, optimize, and operate systems that bring Behavioral AI models to life in real time across production environments.

You’ll package, version, roll out, and observe models to ensure fast, accurate, and accountable predictions, working with researchers to improve deployable performance at scale.

Qualifications

• Deep expertise in production ML serving systems and versioning.
• Experience with low-latency inference optimizations.
• Ability to deploy and monitor ML models across environments.
• Proficiency in Go, Rust, C++, or Java with Python for integration.

Responsibilities

• Design, optimize, and operate systems that bring Behavioral AI models to life in real time.
• Package, version, roll out, and observe models across environments to ensure fast predictions.
• Maintain observability and model lineage from input to outcome.
• Collaborate with researchers to improve deployable model performance.

Skills

Model deployment

Low-latency inference

Go

Rust

C++

Java

Python

System design

Observability

Job description

Yobi is seeking a Machine Learning Engineer focused on Inference and Serving. You will design, optimize, and operate systems that bring Behavioral AI models to life in real time across production environments.

You’ll package, version, roll out, and observe models to ensure fast, accurate, and accountable predictions, working with researchers to improve deployable performance at scale.