Deploying, maintaining, and monitoring the AI/ML systems that power our platform, ensuring scalable, reliable, and production-grade AI solutions, and operationalizing large language models (LLMs) and other ML systems.
Requirements
- Proven experience deploying and maintaining machine learning models in production at scale.
- Hands-on experience with ML lifecycle tooling (MLflow, Kubeflow, SageMaker, Vertex AI, or similar).
- Strong proficiency in Python; familiarity with ML frameworks such as PyTorch or TensorFlow.
- Deep knowledge of containerization (Docker) and orchestration (Kubernetes) for production ML systems.
- Expertise with cloud platforms (AWS, GCP, Azure) for ML deployment and scaling.
- Strong understanding of MLOps best practices, monitoring, and automation.
- Excellent problem-solving skills, with an emphasis on building reliable, scalable systems.
Responsibilities
- Design, implement, and maintain ML deployment pipelines for scalable production systems.
- Operationalize large language models (LLMs) and other AI/ML models, ensuring high availability and reliability.
- Build robust model monitoring, logging, and alerting systems to track performance and detect drift.
- Partner with data scientists to transition models from research/prototype into production-ready deployments.
- Develop CI/CD pipelines for ML workflows, integrating testing, validation, and automated deployment.
- Optimize runtime performance of ML models across cloud platforms (AWS, GCP, Azure) and distributed systems.
- Apply containerization and orchestration (Docker, Kubernetes) to enable reproducible, scalable systems.
Other
- 5+ years of experience as a Machine Learning Engineer, MLOps Engineer, or similar role.
- Collaborate with cross-functional teams to ensure ML systems align with platform goals and business requirements.
- Strong communication and collaboration skills across technical and non-technical teams.
