AI Infrastructure Engineer

About the Role

Join our team as an AI Infrastructure Engineer to design, develop, and optimize the core platforms and services that power our machine learning initiatives. You will create a robust, self-service ML ecosystem that accelerates innovation and enables data scientists and ML engineers to train, deploy, and monitor models efficiently.

Responsibilities

• Design, implement, and maintain high-performance ML training and inference platforms.
• Develop MLOps tools to enable rapid model deployment.
• Optimize the scalability, reliability, and cost efficiency of model training and serving systems.
• Collaborate with researchers to transition experimental voice models into production-ready systems.
• Establish best practices for model versioning, testing, monitoring, and governance.
• Automate data and model pipelines to reduce manual intervention and accelerate experimentation.

Requirements

• 3+ years of experience in Software Engineering or ML Platform/Infrastructure roles, with a focus on distributed systems, cloud services, or MLOps.
• Proficiency in Python, containerization (Docker, Kubernetes), and CI/CD pipelines.
• Strong knowledge of cloud platforms (AWS, GCP, or Azure) and infrastructure-as-code tools (Terraform, CloudFormation).
• Experience with ML frameworks (TensorFlow, PyTorch, or similar) and orchestration tools (Kubeflow, Airflow, or MLflow).
• Deep understanding of data pipelines, model deployment, real-time inference systems, and AI system reliability.
• Strong communication skills and the ability to collaborate across engineering and data science teams.

Nice-to-Haves

• Experience with feature stores, vector databases, or large-scale model training.
• Familiarity with streaming data technologies (Kafka, Spark Streaming, Flink).
• Knowledge of monitoring and observability tools (Prometheus, Grafana, Datadog).
• Contributions to open-source ML/MLOps projects.
• Experience with GPU optimization (TensorRT, ONNX, vLLM, Triton).
• Familiarity with low-latency audio/streaming systems.