Zum Hauptinhalt wechseln
Suchen

Evaluation and Benchmarking for Biomedical Multi-Modal Reasoning Internship

Ort Cambridge, England, Vereinigtes Königreich Anzeigen-ID R-219815 Veröffentlichungsdatum 14/02/2025

About AstraZeneca

AstraZeneca is a global, science-led biopharmaceutical company, developing innovative medicines that benefit millions of patients worldwide! Our internship programs provide hands-on experience in cutting-edge research, allowing students to contribute meaningfully while developing their skills in a collaborative environment.

Introduction to the Role

This internship focuses on developing principled evaluation methods and benchmarks for biomedical multi-modal reasoning, a key challenge in AI-driven healthcare and drug discovery. Current Visual Question Answering (VQA) benchmarks for biomedical applications rely on exact match scoring or LLM-based evaluation, both of which have limitations.

This project aims to establish a more robust evaluation framework tailored to biomedical VQA tasks, ensuring reliable and interpretable AI model assessment. The research will also explore the creation of a biomedical multi-modal benchmark and investigate an internal genomic benchmark, aligning with AstraZeneca’s strategic research priorities.

Accountabilities

As a Summer Intern, you will:

  • Contribute to the development of principled evaluation methods for biomedical VQA tasks.

  • Assist in building and validating a biomedical multi-modal benchmark.

  • Analyze model performance and identify limitations of existing evaluation approaches.

  • Work with AI researchers, data scientists, and domain experts to refine evaluation methodologies.

  • Summarize findings in technical reports and potentially contribute to a research publication.

Essential Skills/Experience

  • Currently pursuing a degree in Computer Science, AI, Bioinformatics, Biomedical Informatics, or a related field.

  • Strong programming skills in Python and experience with machine learning frameworks (e.g., PyTorch, TensorFlow).

  • Familiarity with VLMs, LLMs, multi-modal learning, and model evaluation techniques.

  • Interest in biomedical AI applications and dataset curation for benchmarking.

  • Strong analytical thinking, problem-solving skills, and ability to work in a research-driven environment.

Additional Information

Applications will be open until 28/02/2025. Start date 09/06/2025 - 29/08/2025 and you can expect to hear back from us by the end of March 2025.

At AstraZeneca, we value diversity and inclusion. We welcome applications from all backgrounds and provide accommodations to ensure an equitable recruitment process.

Ready to make an impact? Apply now!

We will ensure that individuals with disabilities are provided reasonable accommodation to participate in the job application or interview process, to perform essential job functions, and to receive other benefits and privileges of employment.

We are an equal opportunity employer and value diversity at our company. We do not discriminate on the basis of race, religion, colour, national origin, sex, gender, gender expression, sexual orientation, age, marital status, veteran status, or disability status. We will ensure that individuals with disabilities are provided reasonable accommodation to participate in the job application or interview process, to perform essential job functions, and to receive other benefits and privileges of employment.



10000036 A UNUN

Mitglied in unserer Talentgemeinde werden

Melden Sie sich an, um als erste(r) die Job-Updates zu erhalten.

InteressensschwerpunkteErfassen Sie die ersten Buchstaben einer Kategorie, und treffen Sie dann eine Auswahl aus den Vorschlägen. Erfassen Sie die ersten Buchstaben eines Ortes, und treffen Sie dann eine Auswahl aus den Vorschlägen. Klicken Sie danach auf „Hinzufügen“, um Ihre Benachrichtigung zu erstellen.

Glassdoor logo Rated four stars on Glassdoor

Großartige Kultur, großartige Arbeitsaufgaben, unterstützendes Management. Rotationsmöglichkeit innerhalb des Unternehmens. Sie schätzen Integration und Vielfalt.