Uni Internship Jan to July 2027 - AI Benchmarking and Automatic Evaluation Framework Development

Synapxe; Singapore; On-site; SGD 11,000 - 22,000; Part time

Job summary

Synapxe invites interns to join the Data Science & AI team to advance the evaluation and benchmarking of Large Language Models (LLMs) for healthcare applications, contributing to robust evaluation frameworks. The role emphasizes developing methodologies, pipelines, and standardized assessments to ensure reliable performance and safety in health tech.

As an intern, you will gain practical experience, work with a multidisciplinary team, and produce dashboards and reports that summarize findings

Qualifications

• Undergraduate currently in Year 2 or Year 3 pursuing a relevant degree.
• Strong proficiency in Python with solid coding fundamentals.
• Basic understanding of statistics and NLP concepts, including evaluation metrics.
• Familiarity with Large Language Models (LLMs) and prompt engineering preferred.
• Independent, fast‑learner, and self‑driven.
• Good team player with strong analytical and communication skills.
• Ability to multitask and work effectively as part of a multidisciplinary team.

Responsibilities

• Conduct literature reviews on AI benchmarking methodologies, evaluation metrics, and healthcare AI validation frameworks.
• Understand and extend existing benchmarking pipelines across healthcare use cases such as question answering, clinical summarization, and diagnosis tasks.
• Refine and experiment with evaluation metrics to improve the assessment of AI model performance.
• Improve evaluation prompt design and assess its impact on scoring reliability and consistency.
• Curate and prepare healthcare evaluation datasets to support benchmarking activities.
• Design and implement standardized benchmarking workflows to improve reproducibility and scalability.
• Perform experiments comparing different models, prompts, and evaluation approaches.
• Analyse benchmarking results to identify model strengths, limitations, and potential risks in healthcare contexts.
• Develop benchmarking dashboards, summary reports, or master benchmarking tables to present findings effectively.
• Document methodologies, evaluation strategies, and experiment results.
• Prepare presentation materials and support knowledge‑sharing activities within the team.

Skills

Python programming

Statistics

NLP concepts

Prompt engineering

Self-driven

Team player

Multitasking

Education

Pursuing degree in Business Analytics, AI Systems, Information Systems, Computer Science, Computer Engineering, Data Science

Job description

Join Synapxe as an intern and see how you can contribute in powering a healthier Singapore. Internship@Synapxe is where curiosity meets impact! You would be able to gain practical experience, hone your skills, and be part of meaningful work that improves health through technology!

As an intern you will join the Data Science & AI team to advance the evaluation and benchmarking of Large Language Models (LLMs) for healthcare applications. As AI adoption continues to grow across healthcare, there is an increasing need for robust, standardized, and domain‑specific evaluation frameworks to assess model performance, reliability, and safety. This internship focuses on enhancing healthcare AI benchmarking capabilities through the development of evaluation methodologies, benchmarking pipelines, and standardized assessment frameworks.

Responsibilities

• Conduct literature reviews on AI benchmarking methodologies, evaluation metrics, and healthcare AI validation frameworks
• Understand and extend existing benchmarking pipelines across healthcare use cases such as question answering, clinical summarization, and diagnosis tasks
• Refine and experiment with evaluation metrics to improve the assessment of AI model performance
• Improve evaluation prompt design and assess its impact on scoring reliability and consistency
• Curate and prepare healthcare evaluation datasets to support benchmarking activities
• Design and implement standardized benchmarking workflows to improve reproducibility and scalability
• Perform experiments comparing different models, prompts, and evaluation approaches
• Analyse benchmarking results to identify model strengths, limitations, and potential risks in healthcare contexts
• Develop benchmarking dashboards, summary reports, or master benchmarking tables to present findings effectively
• Document methodologies, evaluation strategies, and experiment results
• Prepare presentation materials and support knowledge‑sharing activities within the team

Note: The scope of the project may evolve based on organisational priorities. Interns may also be given opportunities to contribute to other ongoing projects and initiatives within the team as required.

Qualifications

• Undergraduate currently in Year 2 or Year 3, pursuing a degree in Business Analytics, Business Artificial Intelligence Systems, Information Systems, Computer Science, Computer Engineering, Data Science, or a related discipline
• Strong proficiency in Python programming, with solid coding fundamentals
• Basic understanding of statistics and natural language processing (NLP) concepts, including evaluation metrics
• Familiarity with Large Language Models (LLMs) and prompt engineering is preferred
• Independent, fast‑learner, and self‑driven
• Good team player with strong analytical and communication skills
• Ability to multitask and work effectively as part of a multidisciplinary team