Machine Learning Operation Engineer (MLOps Engineer)
Core
Design, build, and maintain cloud, API, and deployment infrastructure to power ML solutions across cloud, mobile, and edge environments.
Role type
MLOps Engineer (Infrastructure & Deployment)
Builds
Scalable cloud and Kubernetes infrastructure, RESTful/gRPC APIs, MLOps pipelines, and vector search databases for ML inference.
Domain
Cloud Infrastructure, MLOps, Vector Search, Edge/Mobile ML
Deliverable
production ML models
Required skills
Cloud infrastructure (AWS/GCP/Azure), Kubernetes, Docker/Podman, CI/CD, Python, PostgreSQL/SQL Server, Vector databases (FAISS/LanceDB/Qdrant), MLOps tools (MLflow/Airflow/Kubeflow), Model optimization
Preferred skills
Go/C++/Rust, Edge/mobile ML deployment (ONNX/NCNN/MNN), Monitoring tools (Prometheus/Grafana/ELK/Loki)
Technologies
Kubernetes, Helm, Docker, Podman, FastAPI, Flask, Litestar, PostgreSQL, SQL Server, FAISS, LanceDB, Qdrant, MLflow, Airflow, Kubeflow, ONNX Runtime, NCNN, MNN, Prometheus, Grafana, ELK, Loki
Responsibilities
Design and maintain scalable cloud and Kubernetes infrastructure for ML workloads; Build and maintain RESTful/gRPC APIs for ML inference; Develop MLOps pipelines including model versioning and automated retraining; Support vector search and ML infrastructure; Collaborate on model optimization and deployment across devices.
Seniority
Mid-level, hands-on IC