Research Internship — Constraining Large Language Models at Scale F/M

About NAVER LABS Europe

NAVER LABS Europe is part of the R&D division of NAVER, Korea’s leading Internet portal and a global tech company with a range of services that include search, commerce, content, fintech, robotics and cloud.

About the team

In the Interactive Systems group, we develop AI capabilities that enable robots to interact safely with humans, other robots, and systems. For a robot to be truly useful, it must represent its knowledge of the world, share what it learns, and interact with other agents, particularly humans.

Our research integrates expertise in human-robot interaction, natural language processing, speech, information retrieval, data management, and low-code/no-code programming to create AI components that empower next-generation robots to perform complex real-world tasks.

The position

We are looking for a PhD student in Computer Science, Machine Learning or Deep Learning, or an outstanding Master's student, for a 5–6 month research internship starting in the second semester of 2026. The internship will be hosted at Naver Labs Europe, where you will join the NLP team.

The ability to control the outputs of Large Language Models is a central challenge in NLP and machine learning, with important implications for safety, trustworthiness, reasoning, and alignment.

Building on our line of work on the Distributional Policy Gradient method and related approaches, this internship will investigate new ways of controlling language models under rich and challenging composite constraints, while preserving the formal guarantees that make such methods especially valuable. The exact direction of the project will depend in part on the intern’s profile and interests, but it will lie at the intersection of LLM alignment, controlled generation, reinforcement learning, and probabilistic modeling.

What we're looking for

• Strong familiarity with Large Language Models, including training and fine-tuning.
• A solid command of PyTorch.
• Some knowledge of alignment methods such as RLHF or related techniques.
• The ability to design and run experiments autonomously.
• An interest in mathematically grounded research.

This internship is particularly well suited for candidates who enjoy working on ambitious research problems combining theory, algorithms, and empirical evaluation.

Team Publications

Former interns in the team have regularly been first authors on publications at leading NLP and machine learning venues, reflecting the central role they have played in the research: driving the experimental effort, developing the codebase, and co-authoring the resulting papers.

For examples of previous work in this area, please see the publications below :

• A Distributional Approach to Controlled Text Generation. Khalifa et al. (ICLR, 2021.)
• An Approximate Sampler for Energy-Based Models with Divergence Diagnostics. Eikema et al. (TMLR, 2022.)
• Controlling Conditional Language Models without Catastrophic Forgetting. Korbak et al. (ICML, 2022.)
• On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with No Catastrophic Forgetting. Korbak et al. (NeurIPS, 2022.)
• Aligning Language Models with Preferences through f-Divergence Minimization. Go et al. (ICML, 2023.)
• Guaranteed Generation from Large Language Models. Kim et al. (ICLR, 2025.)
• Whatever Remains Must Be True: Filtering Drives Reasoning in LLMs, Shaping Diversity. Kruszewski et al. (ICLR, 2026.)
• disco: A Toolkit for Distributional Control of Generative Models. Kruszewski et al. (ACL, 2023.)

What we offer

• We foster a collaborative environment dedicated to ambitious, multidisciplinary projects that translate advanced research into impactful, real-world solutions, supported by 30+ years of experience in AI and related fields.
• Flexible work/life balance.

• We are an equal opportunity employer that hires based on skills, experience, and merit. We foster an inclusive and diverse workplace where all qualified candidates are considered fairly, regardless of background.

• We’re based in Meylan, close to Grenoble, a city that offers the perfect balance of urban life, cutting-edge research and technology, and spectacular mountain landscapes that provide countless opportunities to relax, recharge, and enjoy the outdoors.

All applications will be carefully considered, even if not all required skills are met. We value diverse backgrounds and the potential of each candidate, and we offer training to support the development of necessary skills.

NAVER LABS, co-located in Korea and France, is the organization dedicated to preparing NAVER’s future. Scientists at NAVER LABS Europe are empowered to pursue long-term research problems that, if successful, can have significant impact and transform NAVER. We take our ideas as far as research can to create the best technology of its kind. Active participation in the academic community and collaborations with world-class public research groups are, among others, important ways to achieve these goals. Teamwork, focus and persistence are important values for us.

 When applying for this position online, please don't forget to upload your CV and cover letter. Incomplete applications will not be considered.

NAVER LABS Europe is subject to French jurisdiction requiring organisations to stipulate that a job/internship is open to both women and men. None of our jobs/internships are gender specific.

References

Réf: 77db2b06-263a-46a4-9c9e-8c9df3c24c79