Senior MLOps Engineer — Edge & Cloud Inference
Posted Updated
Description
Grid Dynamics seeks a Senior MLOps Engineer to design, build, and operate the ML platform powering inference for a fleet of production robots. You will optimize GPU serving with Triton and own the release lifecycle from IaC to CI/CD, while scaling training pipelines across AWS/GCP.
Collaborate with researchers and robotics engineers to bridge prototype and scalable production. You will manage datasets, model registries, and experiment tracking (MLflow, DVC, Kubeflow), and drive cloud cost
Build and maintain the ML platform powering inference across production robots. Deploy and optimize models on GPUs using NVIDIA Triton for fast, cost-efficient inference. Own end-to-end release lifecycle for ML workloads: IaC (Terraform) and CI/CD (GitHub Actions). Develop scalable training and fine-tuning pipelines on cloud infrastructure (AWS/GCP). Manage datasets, model registries, and experiment tracking (DVC, MLflow, Kubeflow). Control cloud costs across AWS and GCP with smart scaling. Create internal tools/libraries to help data scientists ship models smoothly. Collaborate with ML researchers, CV engineers, and robotics teams to move prototypes to production. Solid foundation in MLOps, taking models from training to production deployment. Proficiency in Python, plus Docker, Terraform, and GitHub Actions. Experience serving ML models on GPUs using NVIDIA Triton and managing ML lifecycle tooling (MLflow, DVC). Hands-on with AWS and/or GCP, including autoscaling and spot/preemptible instances. Flexible schedule Competitive salary Benefits package - medical insurance, Sports program Corporate social events Professional development opportunities Well-equipped officeSkills
Sign in to read and join the discussion.