Site Reliability Engineer

Key Skills

Design, Google Cloud Platform (GCP), Kubernetes-K8s, Machine learning techniques, Python Programming, REDIS

Job Description

Chai is one of the fastest-growing, generative AI startups in Silicon Valley. Our platform has been doubling every three months with over 1 million current daily active users and in-house models optimized for entertainment, outperforming ChatGPT.

Who we are looking for:

We need a focused engineer with 3+ years of experience overseeing and maintaining services to be responsible for our cluster of 500+ GPUs. Ensuring they are healthy and running as expected. You will be working alongside equally talented and driven teammates implementing cutting-edge AI inference engines. We need someone who is reliable and has high standards.

Here are the top 2 reasons why we are not for you:

• Startups are hard. Really hard. If you want an easy life, work somewhere else.
• Adequate performance gets a generous severance package.

Here are the top 2 reasons why you should join us:

• Exponential growth. 1 Million MAU. Be the 14th hire and get us to 100 million MAU.
• Craftsmanship. Build something beautiful.

Requirements:

• Bachelor's degree from a leading academic institution
• 3+ years of experience in designing, analyzing, and troubleshooting large-scale distributed ML systems
• Deep knowledge of GCP and Kubernetes
• Knowledge of KServe is strongly preferred

Here is our tech stack:

• Front end: Python, Flutter, Dart
• Back end: Python, GCP, Redis, Kubernetes

Process:

Exceptionally fast, application to offer within 7 days.

1. Apply here
2. First round video interview, system design interview, then onsite
3. Reference checks, negotiation, and offer