🚀 Intern, Distributed Inference for Multi-Modal Large Language Models (MLLMs) with Agentic AI Orc[...]

Intern, Distributed Inference for Multi‑Modal Large Language Models (MLLMs) with Agentic AI Orchestration

Join InterDigital as an intern focused on distributed inference for MLLMs. This role involves researching, designing, and prototyping distributed inference strategies for multi‑modal large language models.

Summary
Multi‑Modal Large Language Models (MLLMs) can process text, images, audio, and video. Real‑time or constrained environments challenge bandwidth and compute. Distributing inference between client and server, coordinated by an agentic orchestration, offers a promising solution. This internship demonstrates the feasibility of such distributed MLLM inference.

• Survey recent advances in MLLMs and select representative models and agentic architectures.
• Build a reference platform implementing selected models.
• Propose and implement distributed inference strategies in Python.
• Conduct experiments to measure key performance metrics such as latency, data size, and energy consumption.

• Master’s student in Computer Science, Artificial Intelligence, Data Science, or related field.
• Strong background in AI/ML, especially large language models.
• Knowledge of multi‑modal systems (text, vision, speech).
• Proficiency in Python and ML frameworks (PyTorch).
• Ability to conduct research and prototype efficiently.

• Familiarity with distributed systems, networking, bandwidth concepts, ONNX framework.

• Hands‑on experience with state‑of‑the‑art MLLMs.
• Development of agentic based proof‑of‑concept.
• Potential participation in a scientific paper, publication, and patents.

Location : Rennes, France

Equal Employment Opportunity
InterDigital is an equal employment opportunity employer. We do not engage in unlawful discrimination based on protected categories under applicable laws.