Middle MLOps Engineer (Python, FastAPI)

#lookfor #outsource #outstaff #remote #MLOps #MachineLearning #Python #Docker #Kubernetes #CI/CD #MLflow #Kubeflow #Terraform

We are looking for a Middle MLOps Engineer to join our AI/ML infrastructure team on a full-time remote basis.

The specialist will build, automate, and maintain end-to-end ML pipelines and production infrastructure, deploying and serving models, managing CI/CD for ML workflows, and ensuring reliability and scalability of ML systems.

Key responsibilities:
• Design, build, and maintain automated ML pipelines for data preprocessing, training, validation, and deployment.
• Deploy, containerize, and serve ML models using Docker, Kubernetes, and model serving frameworks.
• Set up and manage experiment tracking, model registries, and artifact storage (MLflow, DVC, W&B).
• Implement CI/CD pipelines for ML code, models, and data (GitLab CI, GitHub Actions, Jenkins).
• Build and maintain APIs for model inference (FastAPI, Flask, or specialized serving tools).
• Monitor model performance, data drift, and production quality metrics.
• Manage cloud and on-premise infrastructure for ML workloads (AWS SageMaker, GCP Vertex AI, Azure ML).
• Orchestrate data and ML workflows using Apache Airflow, Kubeflow, or Prefect.
• Optimize model inference latency, throughput, and resource consumption.
• Implement infrastructure-as-code (Terraform, CloudFormation) for ML environments.
• Ensure reproducibility of ML experiments and maintain clear documentation.
• Troubleshoot production ML issues and perform root cause analysis.
• Collaborate with data scientists to productionize research and automate training workflows.
• Manage secrets, access control, and security best practices for ML systems.

Requirements:
• 3+ years of commercial experience in MLOps, ML Engineering, or DevOps with ML focus.
• Strong Python proficiency for automation, pipeline development, and system integration.
• Hands-on experience with Docker and Kubernetes for container orchestration and model serving.
• Practical knowledge of CI/CD tools applied to ML workflows.
• Experience with ML experiment tracking and model management tools (MLflow, DVC, W&B).
• Solid understanding of model serving frameworks (Triton, TensorFlow Serving, BentoML, KServe).
• Experience with SQL and data processing libraries (pandas, NumPy) for pipeline development.
• Familiarity with cloud platforms (AWS, GCP, or Azure) and their ML services.
• Understanding of distributed data processing (Spark, PySpark, Dask).
• Knowledge of infrastructure-as-code (Terraform, Ansible) and configuration management.
• Experience with monitoring and observability tools (Prometheus, Grafana, CloudWatch).
• Understanding of data drift, model degradation, and production quality metrics.
• Strong Git skills and collaborative development workflows.
• Experience with REST API development (FastAPI, Flask) for model inference endpoints.
• English: B2 or higher (written and spoken).

Nice to have:
• Experience with specialized model serving and optimization (ONNX, quantization, pruning).
• Knowledge of feature stores (Feast, Tecton) and feature engineering pipelines.
• Familiarity with NLP, CV, recommender systems, or time-series model deployment.
• Experience with serverless ML deployment (AWS Lambda, Cloud Functions).
• Understanding of GPU computing and CUDA optimization for inference.
• Knowledge of data versioning and lineage tools (DVC, Apache Atlas).
• Experience with service mesh (Istio, Linkerd) for ML microservices.
• Familiarity with compliance and security standards for ML (SOC2, GDPR).
• Contributions to open-source MLOps tools or technical publications.
• Experience with multi-cloud or hybrid cloud ML infrastructure.

Location: Remote, worldwide
Restrictions: Candidates from Egypt, India, Pakistan, and Afghanistan are not considered
English: B2+
Format: Full-time, outsource, outstaff
Contact: ••••••••