AI Engineer Intern (Genève, CH, 1203)

Teoxane; Genf; Hybrid; CHF 20,000 - 33,000; Full time

Job summary

Teoxane Laboratories, based in Geneva, Switzerland, invites applications for a 6-month internship in the IT department's AI Lab as part of Project ChromaDerm. The role focuses on building an image processing pipeline to measure skin color from clinical photographs and on developing a probabilistic model with uncertainty estimation.

We're seeking an ongoing Master’s student in Data Science or related field with strong Python skills (NumPy, pandas, scikit-learn) and image processing (OpenCV,

Qualifications

• Ongoing Master’s in Data Science, Applied Statistics, Engineering, or a related field.
• Strong Python: NumPy, pandas, scikit-learn, and image processing (OpenCV, Pillow).
• Solid applied statistics: variance components, uncertainty quantification, calibration.
• Familiarity with PyTorch; interest in colorimetry (CIELAB), LLMs and RAG is an asset.
• Curious, rigorous, autonomous; works well independently and in a cross-functional team.
• Fluent in English; French is an asset.

Responsibilities

• Build an image processing pipeline sampling skin color at multiple facial locations, with automated quality gating (facial segmentation, rejection of specular highlights, shadows and occlusions).
• Quantify measurement precision: variance decomposition across subject, site, imaging system, viewing angle and visit; repeatability and test–retest analysis.
• Characterize and correct or statistically account for differences between imaging systems.
• Develop a calibrated probabilistic model estimating Fitzpatrick skin type with explicit uncertainty, and a logic for flagging discordant cases for human review.
• Run pre-specified robustness and fairness checks across the measured skin tone range.
• Document methodology, results and code to ensure project continuity.

Skills

Python

NumPy

pandas

scikit-learn

OpenCV

Pillow

PyTorch

colorimetry

English

Education

Master's in Data Science or related

Tools

OpenCV

Pillow

Job description

Select how often (in days) to receive an alert:

Date: Oct 27, 2026

Teoxane Laboratories were established in Geneva, Switzerland, in 2003. They are specialized in the design and manufacturing of hyaluronic acid-based dermal fillers and dermocosmetics. Teoxane strength is to offer a global patient care. Using its products, practitioners are able to fill all kinds of wrinkles, from the finest to the deepest, to restore youthful volume to the face, and to treat the neck and décolleté, with natural results. The strength of Teoxane is also its human size and independence. Teoxane has a total freedom of thoughts, action and innovation which makes the company unique.

In the frame of the growth of our business, we are looking for a:

Contract: 6 months (start date February 2027)

Within the IT department, as part of the AI Lab, this internship contributes to Project ChromaDerm: measuring skin tone objectively and reproducibly from clinical photographs. Teoxane holds a large photographic dataset acquired across multiple studies, sites and imaging systems. The internship builds the measurement layer first – how precisely skin color can be read from these images – and then the predictive model on top of it.

Main activities

• Build an image processing pipeline sampling skin color at multiple facial locations, with automated quality gating (facial segmentation, rejection of specular highlights, shadows and occlusions),
• Quantify measurement precision: variance decomposition across subject, site, imaging system, viewing angle and visit; repeatability and test–retest analysis,
• Characterize and correct or statistically account for differences between imaging systems,
• Develop a calibrated probabilistic model estimating Fitzpatrick skin type with explicit uncertainty, and a logic for flagging discordant cases for human review,
• Run pre-specified robustness and fairness checks across the measured skin tone range,
• In a second phase, as a support project, contribute to other AI Lab initiatives such as Noesis (Teoxane’s internal AI assistant) and LightRAG-based document processing,
• Document methodology, results and code to ensure project continuity.

Your profile

• Ongoing Master’s in Data Science, Applied Statistics, Engineering, or a related field,
• Strong Python: NumPy, pandas, scikit-learn, and image processing (OpenCV, Pillow),
• Solid applied statistics: variance components, uncertainty quantification, calibration,
• Familiarity with PyTorch; interest in colorimetry (CIELAB), LLMs and RAG is an asset,
• Curious, rigorous, autonomous; works well independently and in a cross-functional team,
• Fluent in English; French is an asset.

TEOXANE promotes equal opportunity and places at the heart of its human resources management policy the fight against all forms of discrimination based on age, gender, origin, disability, or any other personal characteristic.