DeepRec.ai
Job Title: MLOps Engineer
Work Arrangement: Remote
Location: Toronto, Canada
Salary: Up-to $125,000 CAD
MLOps Engineer – Real-Time AI Systems
We’re looking for an experienced MLOps Engineer to help deploy and scale cutting-edge ML models for real-time video and audio applications.
You’ll work alongside data scientists and engineers to build fast, reliable, and automated ML infrastructure.
Key Responsibilities
- Build and manage ML pipelines for training, validation, and inference.
- Automate deployment of deep learning and generative AI models.
- Ensure model versioning, rollback, and reproducibility.
- Deploy models on AWS, GCP, or Azure using Docker and Kubernetes.
- Optimize real-time inference using TensorRT, ONNX Runtime, or PyTorch.
- Use GPUs, distributed systems, and parallel computing for performance.
- Create CI/CD workflows (GitHub Actions, Jenkins, ArgoCD) for ML.
- Automate model retraining, validation, and monitoring.
- Address data drift, latency, and compliance concerns.
What You Bring
- 3+ years in MLOps, DevOps, or model deployment roles.
- Strong Python and experience with ML frameworks (PyTorch, TensorFlow, ONNX).
- Proficiency with cloud platforms, Docker, and Kubernetes.
- Experience with ML tools like MLflow, Airflow, Kubeflow, or Argo.
- Knowledge of GPU acceleration (CUDA, TensorRT, DeepStream).
- Understanding of scalable, low-latency ML infrastructure.
Nice to Have
- Experience with Ray, Spark, or edge AI tools (Triton, TFLite, CoreML).
- Basic networking knowledge or CUDA programming skills.
