Uni Internship Jan to May 2026 - Development on Search and Retrieval Strategies

Synapxe is the national HealthTech agency inspiring tomorrow’s health. The nexus of HealthTech, we connect people and systems to power a healthier Singapore. Together with partners, we create intelligent technological solutions to improve the health of millions of people every day, everywhere.
 
Are you someone who enjoys problem solving, has a creative and curious mind, and strives to create a better and healthier tomorrow? If you say yes to all, do check out our website and find out more about Internship@Synapxe.
 
Join Synapxe as an intern and see how you can contribute in powering a healthier Singapore. We aim to deliver the best experience for all interns, to create exponential growth and paving your future in the tech industry.

The objective of this internship is to explore, implement, and evaluate the latest search and retrieval strategies to enhance Generative AI applications. With the rapid advancements in this evolving space, the intern will delve into novel techniques including adaptive and hybrid search, advanced indexing, multimodal considerations, and the latest in vector store technologies. The intern will identify key aspects from this exploration to inform the design and development of new components or improvements for existing search pipelines. A strong emphasis will be placed on understanding and leveraging various cloud functionalities for building robust and scalable search solutions.

The selected intern will participate but not limited to the following:

Phase 1: Exploration and Evaluation of Advanced Retrieval Strategies

Retriever Strategy - Implement and evaluate a diverse set of retrieval strategies:

• Semantic Search: Explore and implement hybrid approach (dense embeddings with sparse).
• Explore multi-stack/cascading retrieval (initial filtering followed by refined re-ranking).
• Embed with multi-modal retrieval.
• Graph-based Retrieval: Implement Graph-RAG techniques for knowledge-intensive retrieval.

Indexing techniques:

• Evaluate various indexing algorithms (i.e., HNSW, IVF, PQ, etc.) within selected vector stores.
• Analyze their performance characteristics, scalability, and suitability for different data types and query complexities.
• Adaptive Retrieval: Research and prototype adaptive retrieval mechanisms that can dynamically adjust the retrieval strategy based on query characteristics or context.

Vector Store Deep Dive:

• Gain familiarity with established vector stores: Milvus, Azure AI Search, AWS Knowledge Base, and Vertex AI Search.
• Explore, compare, and contrast capabilities of other prominent vector stores (i.e., Pinecone, Weaviate, Qdrant, etc.) focusing on aspects like ease of integration, specific capabilities, and managed vs. self-hosted trade-offs.

Cloud Search Capabilities Exploration:

• Investigate and document the search, retrieval, and RAG-support functionalities offered by major cloud platforms (i.e., Azure, AWS, Google Cloud).
• Identify how their managed services can be leveraged for building efficient search pipelines.

Phase 2: Prototyping and Implementing RAG Pipeline with Chosen Strategies in a Project

Pipeline Architecture Design:

• Design a modular RAG pipeline architecture that incorporates the identified strategies from Phase 1 (i.e., hybrid approach with adaptive query handling and contextual re-ranking).

Core Component Implementation/Integration:

• Develop or integrate key components of the designed RAG pipeline in a specified project. This may include:
• Data ingestion and pre-processing

Indexing setup in a chosen vector store

• Implementation of the selected retrieval method(s)
• Mechanisms for augmenting context for answer generation

Additional Responsibilities:
Documentation and Reporting:

• Maintain detailed documentation of research findings, implementation details, and best practices.
• Prepare regular progress reports and presentations for team meetings.
• Performance Evaluation and Optimization:
• Develop benchmarks and metrics to evaluate the performance of implemented strategies.
• Conduct thorough testing and optimization of the RAG pipeline.

Collaboration and Knowledge Sharing:

• Participate in team discussions and brainstorming sessions.
• Share insights and learnings with the broader team through knowledge-sharing sessions or internal workshops.
• Stay Updated with Latest Developments:
• Continuously monitor and research the latest advancements in search and retrieval strategies for Generative AI.
• Attend relevant webinars, conferences, or workshops to stay at the forefront of the field.

About you:

• Be pursuing a Bachelor Degree in Business Analytics, Data Science, Computer Engineering, Computer Science or related discipline
• Graduating in May/Dec 2026 or May 2027
• GenAI Fundamentals:
  • Experience with relevant tools and framework like OpenAI API, LangChain/Llama-Index or open source language models.
  • Preferred: Some exposure with concepts and applications of Generative AI, i.e. Retrieval Augmented Generation.
• Development Tools Proficiency:
  
  • Adept in using tools like VS Code for script development and Jupyter notebooks for exploratory analysis.
  • Preferred: Knowledge of version control with Git is valuable. The intern will attain the knowledge of building pipelines for RAG, understand the key components for an effective search retrieval, and familiarised with the various implementations for agentic workflows.
• Adept in Python syntax, data structures, algorithms including familiarity with common python libraries, and ability to write clean, efficient, well-documented code.
  • Preferred: Back-end development with some exposure to Flask/Fast API
• Good team player with strong analytical and communication skills
• Ability to multitask and work effectively as part of a multidisciplinary team
• Passionate and keen to make a difference to re-imagine the future of HealthTech

#LI-YG1

#LI-LK1