About the role
As an AI/ML Ops Engineer, you'll be responsible for designing, deploying, and maintaining the infrastructure that runs our AI models in production. You'll work on optimizing inference pipelines, managing model deployments, and ensuring our AI systems are reliable, scalable, and cost-effective.
Responsibilities
- Design, build, and maintain scalable ML pipelines for model training, evaluation, and deployment.
- Collaborate with data scientists and AI engineers to ensure smooth handoff from experimentation to production.
- Implement CI/CD pipelines for ML models, including automated testing and validation.
- Develop and maintain monitoring systems for model performance, data drift, and system health.
- Optimize inference pipelines for latency and cost efficiency.
- Implement testing strategies for models, including unit tests, integration tests, and data validation checks.
- Manage containerized deployments using Docker and Kubernetes.
- Ensure compliance with security and data privacy requirements.
Requirements
Experience
- 4+ years of experience in MLOps, DevOps, or infrastructure engineering.
- Experience deploying and managing ML models in production environments.
- Track record of building reliable, scalable systems.
Technical skills
- Strong proficiency in Python and experience with ML frameworks (PyTorch, TensorFlow).
- Experience with containerization (Docker) and orchestration (Kubernetes).
- Familiarity with a major cloud platform and its ML services.
- Experience with CI/CD tools (GitHub Actions, GitLab CI, Jenkins).
- Knowledge of monitoring tools (Prometheus, Grafana, DataDog).
- Experience with infrastructure-as-code (Terraform, Pulumi).
Nice to have
- Experience with LLM deployment and optimization (vLLM, TensorRT-LLM).
- Familiarity with feature stores and model registries (MLflow, Weights & Biases).
- Experience with GPU infrastructure management.