Pranjal comes with more than a decade-long career in Data Science and AI, with a profound understanding across various ML domains. His area of expertise extends to fraud prevention, generative AI, recommendations, search algorithms, and route optimization. A holder of two patents and contributor to multiple academic publications in NLP and ML.
Prior to joining udaan, India’s largest eB2B commerce platform, Pranjal held several key positions at Visa, Ola, and Ping Identity, providing him with a holistic perspective on the application of AI across different industry sectors and verticals.
In the past, Pranjal has been a speaker at various industry forums – ‘Re-Work Deep Learning Summit Asia’ and ‘AZConf at IIT Madras. Pranjal has a Bachelor's and Master's degree in Computer Science from IIT Kanpur.
Agentic workflows combine specialized LLMs, tool usage, and validation techniques to solve complex, real-world tasks. In this session, we will walk through practical design patterns and strategies to build robust multi-agent systems that are scalable, grounded, and capable of self-correction.
We will explore how to structure interactions between agents using routing, sequential chaining, and asynchronous orchestration. Through real-world demos, we’ll show how structured outputs, task guardrails, and grounding with multimodal models (VLMs, audio, OCR) can be combined to ensure reliable performance. This session is hands-on, code-rich, and designed to equip attendees with implementation-ready insights.
The session will provide practical examples and demonstrations of multi-agent systems, including: asynchronously coordinating agents for parallel data processing or project management; sequential agent flows for tasks like document extraction, summarization, and translation; a Router Agent for directing customer support queries; a VLM agent for image analysis and object identification; a Query-to-Dashboard system for generating visualizations from natural language queries; and an audio processing agent that transcribes spoken commands and acts upon them.
Read MoreManaging and scaling ML workloads have never been a bigger challenge in the past. Data scientists are looking for collaboration, building, training, and re-iterating thousands of AI experiments. On the flip side ML engineers are looking for distributed training, artifact management, and automated deployment for high performance
Read MoreManaging and scaling ML workloads have never been a bigger challenge in the past. Data scientists are looking for collaboration, building, training, and re-iterating thousands of AI experiments. On the flip side ML engineers are looking for distributed training, artifact management, and automated deployment for high performance
Read More