3 months ago
Bengaluru, IndiaStaff+
Responsibilities
- Design and architect scalable ML systems infrastructure for deploying and serving large video models in production.
- Define technical strategy and best practices for model development, evaluation, monitoring, selection, optimization, and fine-tuning.
- Translate complex AI research into production-ready systems in collaboration with research and engineering teams.
- Champion MLOps practices including model versioning, A/B testing, and continuous evaluation frameworks.
- Drive performance optimization to meet model latency and throughput requirements at scale.
- Establish evaluation metrics, benchmarking, and continuous improvement processes.
- Mentor and guide engineers on architecture, design decisions, and technical trade-offs.
Requirements
- 10+ years of experience in software architecture or systems design, including 5+ years focused on ML/AI systems architecture.
- Deep expertise in scalable machine learning systems, data pipelines, model serving, and inference optimization.
- Strong background in large-scale distributed systems, cloud infrastructure, and containerization.
- Hands-on experience with PyTorch, TensorFlow, MLflow, Kubeflow, and Airflow.
- Expert-level proficiency in at least one of Python, Java, or C++.
- Deep understanding of video processing pipelines, H.264, HEVC, AV1, and streaming technologies.
- Experience deploying and scaling video understanding or multimodal AI models in production.
- Knowledge of quantization, pruning, knowledge distillation, and efficient inference.
- Excellent communication skills and the ability to align technical and non-technical stakeholders.
- Bachelor's or master's degree in computer science or a related field, with 10–13 years of development experience preferred.
Tech Stack
Categories
About Hotstar
We’ve moved! 🌟 Follow us on @JioHotstar for all the latest stories, updates & more.