Get a reply from this employer
Your resume and cover letter, tailored to exactly what they’re hiring for.
Inria in France seeks a First Stage Researcher for an internship under the ANR FM2AI project, collaborating with APHP to systematically evaluate LLM-based agents that use medical imaging tools for abdominal CT question answering. The study focuses on accuracy, efficiency, tool contribution, and faithfulness of reasoning.
Applicants should be in the final year of engineering or enrolled in a Master 2, with strong Python/PyTorch skills and experience with LLMs and tool calling.
Inria, the French national research institute for the digital sciences
Organisation/Company Inria, the French national research institute for the digital sciences Research Field Computer science Researcher Profile First Stage Researcher (R1) Application Deadline 28 Feb 2027 - 00:00 (UTC) Country France Type of Contract Temporary Job Status Full-time Hours Per Week 38.5 Offer Starting Date 1 Mar 2027 Is the job funded through the EU Research Framework Programme? Not funded by a EU programme Reference Number 2026-10733 Is the Job related to staff position within a Research Infrastructure? No
In the context of the ANR FM2AI, and in collaboration with APHP, the aim of this internship is to systematically evaluate LLM-based agents that combine reasoning with specialized medical imaging tools for abdominal CT question answering, focusing on their accuracy, computational efficiency, the contribution of individual tools, and the faithfulness of their reasoning.
Scientific context: Foundation models for CT have multiplied: vision‑language encoders (CT‑CLIP [10], Merlin [8], Jolia [15]), generative modelsthat answer questions about a volume (CT‑CHAT [10], MedGemma 1.5 [11]), large pretrained encoders (Pillar‑0 [12], Curia[13], FlexiCT [14]) and segmentation tools (TotalSegmentator [9]). On their own, they still fail on tasks that require localizing,measuring and then reasoning. Hence the idea, following ReAct [16], of delegating the reasoning to an LLM that calls these models as tools. Born in chestradiography with MedRAX [7], this paradigm now reaches 3D CT: CT‑Agent [2], 3DMedAgent [5], CT‑Flow [6], INFORM‑CT [3]. The most striking result comes from RadAgent [1]: without any training, an agent orchestrating CT‑CHAT, CT‑CLIP, TotalSeg‑mentator and a general‑purpose 2D VLM (Gemma 3 [19]) outperforms CT‑CHAT on report generation. On DeepTumorVQA[4], a fine‑tuned 2D VLM even beats the best 3D model (66.3% vs. 59.8%), but without measurement tools, all models makeup quantitative values. The problem: each system comes with its own harness (agent loop, tools, prompts), data and metrics, so it is impossible totell what actually makes the difference. Abdominal CT, less studied than the chest, is an ideal testbed: DeepTumorVQA pro‑vides questions with verifiable answers on 9,262 public volumes, organized by level (recognition, measurement, reasoning),together with a standardized tool environment.
Research questions:
Possible extension, depending on results and interest: the verifiable answers of DeepTumorVQA make it a natural testbedfor reinforcement learning of agents [21] (e.g. GRPO on a small LLM).
Specific Requirements
This internship is strictly open to students in the final year of an engineering degree or enrolled in a second-year Master's programme (M2), preferably specializing in machine learning, artificial intelligence, or a closely related field. Applicants should have strong programming skills in Python and PyTorch, a solid background in machine learning, and an interest in rigorous scientific experimentation. Familiarity with large language models (LLMs), agentic AI, or evaluation methodologies would be an advantage. Prior experience in medical imaging is appreciated but not required. Applications from candidates outside the specified academic levels will not be considered.
Recruitment is subject to the candidate obtaining the required authorization to access the laboratory, which is classified as a Zone à Régime Restrictif (ZRR).
Languages FRENCH Level Basic
Languages ENGLISH Level Good