BJAK is looking for an MLOps Engineer to join our team in a fully remote capacity. You will be responsible for fine-tuning state-of-the-art models, designing evaluation frameworks, and bringing AI features into production, ensuring they are safe, trustworthy, and impactful at scale.

What You'll Do

Run and manage open-source models efficiently, optimizing for cost and reliability
Ensure high performance and stability across GPU, CPU, and memory resources
Monitor and troubleshoot model inference to maintain low latency and high throughput
Collaborate with engineers to implement scalable and reliable model serving solutions

What We're Looking For

Experience with model serving platforms such as vLLM or HuggingFace TGI
Proficiency in GPU orchestration using tools like Kubernetes, Ray, Modal, RunPod, LambdaLabs
Ability to monitor latency, costs, and scale systems efficiently with traffic demands
Experience setting up inference endpoints for backend engineers