Titulo Estágio
RAG Pipeline Optimization and Automation
Áreas de especialidade
Sistemas Inteligentes
Local do Estágio
Coimbra
Enquadramento
Intermedia’s Retrieval-Augmented Generation (RAG) pipeline powers internal AI tools like our FAQ bot by integrating dynamic content from documents and web sources. While already production-grade, the current setup requires enhancements to scale effectively, improve precision and enable real-time monitoring. This internship focuses on optimizing and automating core components of the pipeline to strengthen the reliability, accuracy and observability of our AI systems.
Objetivo
- Improve scalability and performance of the RAG pipeline
- Implement intelligent caching and query optimization strategies
- Design real-time alerting and feedback mechanisms
- Evaluate performance improvements through experimentation
- Automate ingestion, indexing, and fallback processes
- Lay the foundation for adaptive, self-improving knowledge systems
Plano de Trabalhos - Semestre 1
- Onboard to the RAG architecture and supporting infrastructure
- Analyze current pipeline components (LangChain, re-ranking, indexing)
- Research and prototype caching strategies to reduce latency and cost
- Implement basic observability and alerting for RAG failure scenarios
- Begin designing feedback loop integration (e.g., correction capture, model tuning)
Plano de Trabalhos - Semestre 2
- Extend pipeline with automated content ingestion and indexing workflows
- Introduce query optimization methods (rewriting, translation, routing)
- Build evaluation metrics and dashboards for tracking accuracy and relevance
- Conduct controlled experiments:
- RAG with vs. without caching and re-ranking
- Feedback impact on accuracy
- Alerting coverage and sensitivity
- Final presentation and documentation
Condições
- Monthly stipend of €900, based on a full-time commitment (40 hours per week)
- Hybrid work model: interns are expected to work from the company office 2–3 days per week
- PC or Mac for the duration of the internship
- Integration into a Product Area team, working closely with engineers and stakeholders
- A mentor will be assigned to support the intern’s development and success
Observações
What We Are Looking For:
- Self-motivated individuals with a strong desire to learn and a collaborative mindset
- Final-year Master’s students in Computer Science, Artificial Intelligence, Engineering or related fields
- A solid understanding of software architecture fundamentals
- Demonstrated experience with at least one relevant programming language or technology (e.g., Python, Java, .NET or C/C++)
- A genuine interest in software design and development
- Enthusiasm for CCaaS/UCaaS, AI/ML or platform development
Orientador
António Simões
asimoes@intermedia.com 📩