Swathy Santhoshkumar
Forward Deployed Engineer-Senior Manager at Accenture
Tampa, Florida, United States
Actions
Swathy Santhosh is a seasoned software engineer with over 15 years of experience in the IT industry, playing multiple roles spanning global teams. She has a passion for full-stack engineering and has a keen eye for user experience for the products that she leads. She has led engineering teams developing mission-critical applications across a wide variety of industries such as financial services, health care, and logistics.
While she isn't in front of her computer, she dabbles in creating mural arts or canvas paintings based on whatever inspires her and hopes to someday focus a lot more time on the arts. She is also an avid traveller and is always in search of her next dream destination.
Links
Area of Expertise
Topics
From Resume Pile to Ranked Shortlist: A Production RAG System on OpenSearch
This session walks through a production RAG system that turns a pile of unstructured resumes into a searchable, rankable talent pool. We cover the full pipeline, from ingestion to retrieval to grounded answers with Claude, and focus on the engineering decisions that actually matter when you move from a weekend prototype to something reliable in production.
Audience Takeaways:
- How to design an ingestion pipeline for real-world, semi-structured documents.
- Why retrieval strategy matters more than model choice for search quality.
- How to tune OpenSearch for the right balance of speed and accuracy.
- Where an LLM genuinely adds value on top of retrieval, and where it just adds cost
Building AI native applications - Software Engineering for the Agentic era
The software engineering landscape is on the brink of a revolution. For decades, the iterative software development cycle has been driven by human-centric processes, producing tools and applications primarily for human consumption. The rise of Generative AI and AI agents is poised to fundamentally transform this paradigm, introducing a new, powerful actor that acts as the builder, the tool, and the consumer.
This session will explore the profound impact of this shift, providing software engineers with the insights and strategies needed to thrive in an AI-native world. We will move beyond the hype to discuss practical techniques and a new mindset for navigating this change.
Key topics covered will include:
- Shifting Your Thinking: Re-evaluating the traditional development cycle and adopting a new perception where systems are built not just for human users but also for AI agents.
- Adopting AI-Powered Tools: Integrating AI agents into your development workflow for tasks like code generation, automated documentation, and managing complex engineering processes.
- Building for an Agentic Future: Designing and developing systems that are "agent-friendly" from the ground up, focusing on concepts like model context protocol (MCP) and exposing tools and APIs that enable seamless interaction between agents.
By the end of this session, attendees will have a clear understanding of what it means to work in an AI-native engineering cycle and will be equipped with actionable strategies to prepare themselves and their teams for the future of software development.
Target Audience:
- Backend API Developers/Engineers
- Data engineers
- AI and Agent developers
Key Takeaways:
1. A Mindset Shift is Non-Negotiable: The future of software engineering requires moving beyond human-centric design to actively build systems and processes that are compatible with and optimized for interaction with AI agents.
2. Your Tools Will Change, and So Should You: Developers must embrace and integrate AI-powered tools and agents into their daily workflow, not as a replacement for their skills, but as an essential part of a more efficient and innovative development cycle.
3. The Future is Agent-Friendly: Designing for interoperability is key. The most successful systems will be those built with a modular approach, exposing clear and accessible APIs and tools that allow seamless communication and collaboration with a growing ecosystem of AI agents.
Production Ready RAG with Ragas framework
Building a RAG application takes a weekend; making it production-ready takes months. For engineers, the biggest bottleneck is evaluation: relying on manual spot-checking is slow, unscalable, and makes tracking regressions impossible.This deeply technical session covers how to treat LLM evaluation like software engineering. We will dive into the architecture of Ragas, exploring how it uses LLMs-as-a-Judge to quantify system performance. We will break down the math and logic behind the RAG Triad such as Faithfulness, Answer Relevance, and Context Precision/Recall. You will learn how to bootstrap your testing with automated, evolutionary synthetic test data generation. Finally, we will demonstrate how to embed Ragas directly into your GitHub Actions or CI/CD pipelines to automatically block hallucinations before code hits production.
Audience Takeaways
Algorithmic Evaluation: Understand the internal prompt-logic and scoring mathematics Ragas uses to calculate metrics.
Isolating the Failure Point: Learn to pinpoint whether a bad user response is a retrieval failure (vector DB) or a generation failure (LLM).
Automated Test Generation: Master the "evolutionary query" method to automatically synthesize diverse, production-grade test datasets from your raw documents.
Continuous Integration for AI: Walk away with an architectural blueprint to build an automated, metric-driven evaluation step inside your CI/CD pipeline.
Swathy Santhoshkumar
Forward Deployed Engineer-Senior Manager at Accenture
Tampa, Florida, United States
Links
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top