MLOps Architect: Scalable Training & Pipelines

Arrayo; Massachusetts; On-site; USD 130,000 - 185,000; Full time

Job summary

Arrayo is seeking an MLops Engineer to lead the scaling of machine learning training pipelines and ensure robust end-to-end workflows. The role focuses on Flyte, GPU-optimized Kubernetes, Docker, and distributed training frameworks like Ray to optimize ML infrastructure.

You will orchestrate workflows, scale multi-node GPU training, and collaborate with data scientists to productize experiments while ensuring reproducibility and cost efficiency.

Qualifications

• Experience with GPU scheduling on Kubernetes and cluster autoscaling.
• Hands-on with Flyte or similar tools (Airflow, Prefect).
• Deep knowledge of distributed ML training (e.g., PyTorch DDP, Ray, Horovod).

Responsibilities

• Develop and maintain ML workflows using Flyte to manage training, testing, and deployment.
• Scale large-scale ML training systems on GPU-backed Kubernetes clusters with auto-scaling and tuning.
• Implement distributed model training pipelines using Ray for parallelization and efficiency.
• Design, build, and optimize Docker images for ML workloads with reproducibility and security.
• Debug and optimize GPU utilization, memory, and compute bottlenecks during training and inference.
• Integrate monitoring for ML jobs, track resource consumption, and enforce cost-efficient resource usage.
• Collaborate with data scientists and ML engineers to productize and scale ML experiments.

Skills

Workflow orchestration

Distributed computing

GPU optimization

ML training

Collaboration with data scientists

Tools

Kubernetes

Flyte

Docker

Ray

PyTorch DDP

Horovod

CUDA

NCCL

GitHub Actions

ArgoCD

Prometheus

Grafana

Job description

Arrayo is seeking an MLops Engineer to lead the scaling of machine learning training pipelines and ensure robust end-to-end workflows. The role focuses on Flyte, GPU-optimized Kubernetes, Docker, and distributed training frameworks like Ray to optimize ML infrastructure.

You will orchestrate workflows, scale multi-node GPU training, and collaborate with data scientists to productize experiments while ensuring reproducibility and cost efficiency.