ML Ops Engineer - Remote

Overview

The ML Ops Engineer will transform language models into real-world applications, working with a global team to build impactful AI solutions.

In Short

• Run and manage open-source models efficiently.
• Ensure high performance across GPU, CPU, and memory resources.
• Monitor and troubleshoot model inference.
• Collaborate with engineers for scalable model serving solutions.
• Work in a flexible remote arrangement.
• Participate in decision-making with a flat structure.
• Receive top-of-market compensation and bonuses.
• Enjoy various employee perks and benefits.
• Be part of a high-performance team focused on global impact.
• Contribute to building intelligent financial systems.

Requirements

• Experience with model serving platforms like vLLM or HuggingFace TGI.
• Proficiency in GPU orchestration tools.
• Ability to monitor latency and scale systems.
• Experience setting up inference endpoints.

Benefits

• Flat structure & real ownership.
• Flexibility in work arrangement.
• High-impact role with visibility across teams.
• Health, dental & vision insurance.
• Unlimited, flexible time off.