Internship: R&D AI fairness intervention based on AI explainability F/M

Key Skills

Aartificial intelligence, Data science techniques, Effective communication skills, Machine learning techniques, Python Programming, PyTorch, TensorFlow

Job Description

We help the world run better

Our company culture is focused on helping our employees enable innovation by building breakthroughs together. How? We focus every day on building the foundation for tomorrow and creating a workplace that embraces differences, values flexibility, and is aligned to our purpose-driven and future-focused work. We offer a highly collaborative, caring team environment with a strong focus on learning and development, recognition for your individual contributions, and a variety of benefit options for you to choose from.Apply now! 

What you'll do

Context: As AI systems become more prelavent in our daily lives, it is essential to ensure that these systems are fair, transparent, ethical. However, AI models are susceptible to unfair bias, whose sources could be multiple. Therefore, we are seeking to gain a deeper understanding of the AI model and how unfair bias may be present and perpetuated in the final decision.

The objective of this internship is to identify and mitigate unfair bias in AI models by using AI explainability, particularly feature importance (SHAP, LIME,…).

In this role:

• You will design baseline AI models on benchmarks datasets and identify potential sources of unfair bias.
• You will then work to mitigate the bias by experimenting with various AI explainability techniques.
• You will also use statistical analysis and experimental design to analyze model performance and identify areas for improvement in terms of utility-fairness tradeoff.
• As part of the internship, you may also be expected to write a report documenting your findings and deliver clear and commented code for future reference.

What you bring

• University level: Last year of MSc, or beyond, in Computer Science, Data Science or related field,
• Strong programming skills in Python,
• Experience with Machine Learning libraries such as scikit-learn, Pytorch or TensorFlow,
• Familiarity with AI explainability techniques such as SHAP, LIME,
• Familiarity with academic research is a plus,
• Fluency in English (working language), good oral and written communication skills.

• Internship of 4-6 months
• Start date: as soon as possible

Meet your team

This internship is based in the SAP Labs France, in Sophia-Antipolis. The work will be conducted under the SAP Security Research program, with the Trustworthy AI team that focuses on developing AI solutions that are private, fair and transparent.

We build breakthroughs together

SAP innovations help more than 400,000 customers worldwide work together more efficiently and use business insight more effectively. Originally known for leadership in enterprise resource planning (ERP) software, SAP has evolved to become a market leader in end-to-end business application software and related services for database, analytics, intelligent technologies, and experience management. As a cloud company with 200 million users and more than 100,000 employees worldwide, we are purpose-driven and future-focused, with a highly collaborative team ethic and commitment to personal development. Whether connecting global industries, people, or platforms, we help ensure every challenge gets the solution it deserves. At SAP, we build breakthroughs, together.