Requirements

Expected technologies

Prometheus

Grafana

Redis

Aerospike

MapReduce

Spark

Flink

Kafka

Docker

Kubernetes

TensorFlow

PyTorch

Spark ML

Python

Go

Optional technologies

Seldon

Triton

ONNX

ONCL

TensorRT

AWS

Ruby on Rails

React

Our requirements

• 6+ years of industry experience with a Master's degree or 3+ years of industry experience with a PhD degree.
• Extensive industry experience in low latency, high throughput distributed microservices.
• Extensive experience with machine learning serving system design, architecture, real time monitoring/alerting components (e.g., Prometheus/ Grafana), and distributed cache systems (e.g., Redis/Aerospike).
• Familiarity with CI/CD, ETL, big data tools, and mainstream ML libraries (e.g., MapReduce, Spark, Flink, Kafka, Docker, Kubernetes, TensorFlow, PyTorch, Spark ML, etc.).
• Solid theoretical background in machine learning or data mining and strong conceptual, problem solving, and analytical skills.
• Knowledge on testing frameworks for online A/B testing, canary, blue-green deployment.
• Extensive programming experience in Python, Go or other OOP languages and familiarity with data structures, algorithms and software engineering principles.
• Strong communication and interpersonal skills to drive cross-functional partnerships.
• Ability to work in a fast-paced environment, quickly debug issues, provide proof of concept solutions and apply the changes to production.

Optional

• Knowledge about ML serving technologies, such as Seldon, Triton, ONNX, ONCL, TensorRT.
• Knowledge about Amazon Web Services (AWS).
• Experience with the advertising industry and real-time bidding (RTB) ecosystem.
• Full stack experience with Ruby on Rails and React.

Your responsibilities

• Design and develop highly scalable, real-time machine learning infrastructure with extremely high throughput and low latency conditions, to support the entire advertising business in Samsung.
• Explore and optimize our current machine learning serving system to ensure 5 nines uptime (continuous availability).
• Research the latest machine learning serving technologies and keep up-to-date with industry trends and developments.
• Experiment with new machine learning serving architecture ideas tailored to our environment and create quick prototypes/ proof-of-concepts.
• Collaborate with different internal ML teams (e.g., model engineers, ML platform, and MLOps) to build a world-class ML infra for advertising platform in the industry.
• Closely work with cross-functional partner teams in global settings to deliver new ML features and solutions and achieve business objectives.
• Mentor junior engineers and provide technical guidance.
• Learn quickly and adapt to a fast-paced working environment.