Master Internship - Tool‐augmented LLM agents for abdominal CT question answering: benchmarking, tool attribution and reasoning faithfulness

Inria

Gif-sur-Yvette

Hybrid

EUR 12,000 - 18,000

Full time

36 hours ago
Be an early applicant

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Benefits offered by this job

Transport reimbursement
Long leave allowance
Teleworking option
Equipment provided
Social events

Job summary

Inria Saclay invites applications for a Master Internship focused on tool-augmented LLM agents for abdominal CT question answering. You will benchmark reasoning with medical imaging tools, analyze tool contributions and ensure faithfulness of reasoning, in collaboration with APHP.

The project reviews state-of-the-art CT models and asks you to systematically evaluate agents across accuracy and efficiency, with an emphasis on rigorous experimentation and reproducible results.

Qualifications

  • Pursuing a Master’s degree in ML or engineering with strong programming skills.
  • Experience in Python and PyTorch for ML experiments and evaluation.
  • Familiarity with LLMs, agent-based AI, and evaluation methodologies.

Responsibilities

  • Benchmark LLM-based agents that combine reasoning with medical imaging tools for CT QA.
  • Assess tool contributions and measure accuracy and efficiency.
  • Investigate faithfulness of the agent’s reasoning and prompts.
  • Extend experiments to ablations and reproducible evaluation.

Skills

Python
PyTorch
LLMs
Agent frameworks
Evaluation methodologies

Education

Master’s degree in ML

Tools

Hugging Face
vLLM
Tool calling

Job description

Master Internship - Tool‐augmented LLM agents for abdominal CT question answering: benchmarking, tool attribution and reasoning faithfulness

Created in 2008, the Inria Saclay Center is located at the heart of the Paris-Saclay scientific and technological excellence cluster, which alone accounts for 15% of French research. Serving the development of the Université Paris-Saclay and the Institut Polytechnique de Paris, the Inria Saclay center employs 80 people in research support services and 500 scientists of 54 nationalities.

Benefiting from continuous growth, the center now has a total of 42 project-teams and two in the process of being created, including 21 jointly with the Institut Polytechnique de Paris, 16 with the Université Paris-Saclay, as well as 7 Inria EPs, including one in collaboration with Onera and one with the Pôle Universitaire Centre Val de Loire. These research teams are spread over more than ten sites.

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:
1. What makes a good agent, and at what cost? Compare harnesses and open‑source LLMs run locally (Qwen3 [17], gptoss
[18], Gemma 4 [22]…) on the same task, and map the accuracy–cost frontier (tokens, latency, GPU memory).
2. Which tools really matter? Systematic ablations and attribution of performance to each tool (segmentation, measurements,
2D or 3D VQA such as MedGemma 1.5 [11], foundation models).
3. Is the agent’s reasoning faithful? When the agent justifies its answer, does it describe what actually determined it?

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).

Bibliographic study

Programming in PyTorch

Use of distant GPU servers

Scientific presentations and reporting

Ablation studies and benchmarking

  • Master 2 in machine learning or final year of engineering school.
  • Good command of Python and PyTorch; taste for rigorous experimentation.
  • A plus: experience with LLMs (Hugging Face, vLLM, tool calling), agent frameworks or evaluation methodology.
  • No prior medical knowledge is required. A first experience with 3D imaging (NIfTI, DICOM, MONAI) is appreciated butcan be acquired during the internship.
  • Fluent French or English; comfortable reading scientific papers in English.
Avantages
  • Partial reimbursement of public transport costs
  • Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
  • Possibility of teleworking and flexible organization of working hours
  • Professional equipment available (videoconferencing, loan of computer equipment, etc.)
  • Social, cultural and sports events and activities

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).

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Master Internship - Tool‐augmented LLM agents for abdominal CT question answering: benchmarking, tool attribution and reasoning faithfulness
Master Internship - Tool‐augmented LLM agents for abdominal CT question answering: benchmarking, tool attribution and reasoning faithfulness

Inria, the French national research institute for the digital sciences • France

Hybrid
EUR 13,000 - 17,000
Partial reimbursement of public travel
7 weeks of annual leave + RTT days
Teleworking possible
+2
Master Internship - Tool‐augmented LLM agents for abdominal CT question answering: benchmarking, tool attribution and reasoning faithfulness
Master Internship - Tool‐augmented LLM agents for abdominal CT question answering: benchmarking, tool attribution and reasoning faithfulness

Inria Gif-sur-Yvette • Gif-sur-Yvette

On-site
EUR 8,900 - 16,000
Master Internship in AI for biological microscopy
Master Internship in AI for biological microscopy

Inria • Saclay

Hybrid
EUR 12,000 - 17,000
Teleworking possible
Flexible working hours
Professional equipment provided
+1
Intern: Tool-Enhanced LLM Agents for Abdominal CT QA
Intern: Tool-Enhanced LLM Agents for Abdominal CT QA

Inria Gif-sur-Yvette • Gif-sur-Yvette

On-site
EUR 8,900 - 16,000
Ml Internship - Learning from radiology reports to detect cancer on CT
Ml Internship - Learning from radiology reports to detect cancer on CT

StartX • Paris

Hybrid
EUR 12,000 - 21,000
Competitive salary
Premium computing hardware
Healthcare access
Research Intern
Research Intern

DeepHealth • Paris

Hybrid
EUR 17,000 - 28,000
AI Research Internship: Hyperspectral Muscle Imaging
AI Research Internship: Hyperspectral Muscle Imaging

Inria • France

Hybrid
EUR 12,000 - 17,000
Teleworking possible
Flexible working hours
Professional equipment provided
+1
Master Internship: Tool-augmented LLMs for Abdominal CT QA
Master Internship: Tool-augmented LLMs for Abdominal CT QA

Inria, the French national research institute for the digital sciences • France

Hybrid
EUR 13,000 - 17,000
Partial reimbursement of public travel
7 weeks of annual leave + RTT days
Teleworking possible
+2
Intership Agentic Multimodal AI for Understanding and Reasoning over Complex Technical Documents-H/F
Intership Agentic Multimodal AI for Understanding and Reasoning over Complex Technical Documents-H/F

CEA • Saclay

On-site
EUR 10,000 - 12,000
ML Internship: Foundation Models for MS MRI Diagnosis
ML Internship: Foundation Models for MS MRI Diagnosis

Raidium • Paris

Hybrid
EUR 20,311 - 24,328
Competitive salary
Access to premium computing hardware