About InterDigital
InterDigital is a global research and development company focused primarily on wireless, video, artificial intelligence (“AI”), and related technologies. We design and develop foundational technologies that enable connected, immersive experiences in a broad range of communications and entertainment products and services. We license our innovations worldwide to companies providing such products and services, including makers of wireless communications devices, consumer electronics, IoT devices, cars and other motor vehicles, and providers of cloud-based services such as video streaming. As a leader in wireless technology, our engineers have designed and developed a wide range of innovations that are used in wireless products and networks, from the earliest digital cellular systems to 5G and today’s most advanced Wi-Fi technologies. We are also a leader in video processing and video encoding/decoding technology, with a significant AI research effort that intersects with both wireless and video technologies. Founded in 1972, InterDigital is listed on Nasdaq.
InterDigital is a registered trademark of InterDigital, Inc.
For more information, visit: www.interdigital.com .
Summary
The objective of this internship is to investigate how Reinforcement Learning (RL) techniques can improve the energy efficiency of adaptive video streaming while maintaining a high Quality of Experience (QoE) for end users. The study will consider optimization opportunities across the entire streaming chain, from video encoding and bitrate-ladder generation to content delivery through Multi-CDN architectures [1], client-side Adaptive Bitrate (ABR) selection, decoding, and display.
Building on recent research in energy-aware adaptive streaming [2] and reinforcement-learning-based Multi-CDN optimization [3], the internship will explore how energy consumption can be dynamically incorporated into streaming adaptation decisions, alongside traditional criteria such as video quality, rebuffering, latency, throughput, delivery cost, and resilience.
The work will investigate RL-based optimization strategies at different levels of the streaming chain. At the client side, RL models may dynamically adjust the cost functions, weighting parameters, or decision criteria of existing heuristic-based energy-aware ABR algorithms. Such adaptation may consider network and playback conditions, device energy policies, device characteristics and operating conditions, as well as the user's viewing context.
At a broader system level, the internship will also investigate the joint optimization of video representation selection and CDN/delivery-pathway selection. Particular attention may be given to Multi-Agent Reinforcement Learning (MARL), where multiple agents responsible for different adaptation decisions cooperate to achieve a common energy-efficiency and QoE objective. This includes investigating coordination between agents to avoid conflicting optimization decisions.
The intern will first review existing approaches and identify the most influential parameters, decision points, and promising RL-based optimization strategies. Selected solutions will then be implemented and evaluated on an end-to-end adaptive streaming platform. A benchmark will quantify the achievable energy savings, assess their impact on QoE and other performance metrics, and compare the proposed solutions with conventional adaptive streaming and independently optimized approaches.
[1] Ali C. Begen , Yuriy Reznik , Daniel Silhavy (DRAFT) SVTA5078: Architectures for Multi-CDN Switching - SVTA
[2] Baptiste Boutaud De La Combe (2026) Energy-Aware Adaptive Video Streaming Using Deep Reinforcement Learning: Master Thesis . Masters thesis, KTH University.
[3] Joshi, Chidambar (2025) Video Streaming Optimizations via Collaborative Multi-CDN Selection with Deep Reinforcement Learning . Masters thesis, Concordia University.
Responsibilities
Conduct a state-of-the-art review, identifying the…