Kartik Nighania

Kartik Nighania

MLOps Engineer

About

Kartik Nighania, an esteemed figure in AI, specializes in MLOps and is currently an engineer at Typewise in Europe. With over seven years of industry experience, Kartik's expertise spans diverse domains such as computer vision, reinforcement learning, NLP, and Gen AI systems. Previously, as Head of Engineering of a YCombinator-backed startup, Kartik spearheaded successful ventures in AI focusing on infrastructure scaling, team leadership, and MLOps implementation. His contributions to academia include publications in top journals and projects undertaken for the Government's Ministry of Human Resource Development (MHRD).

 Spinning up an agent demo is easy; deploying one that works alongside your human employees is not. In this hack session, we'll build a scalable, production-grade AI employee designed to 10x your eng team's throughput, and confront the real challenges along the way: auth and identity, guardrails, human-in-the-loop checkpoints, MCP-based tool integration, agent skills, secure sandboxed execution, cost control, and observability. We'll walk through the roadblocks teams hit moving from prototype to production, and the architectural patterns that make agents cost-effective and reliable enough to trust alongside human teammates.

Read More →

In this hands-on workshop, participants will learn how to build, deploy, scale, and monitor multi-agent workflows exactly the way it's done in a production environment at scale. 

We'll cover agent architecture fundamentals like multi-agent systems, MCP, context engineering and then build real-world agents with tool calling, RAG, memory, and human-in-the-loop workflows.

The workshop goes beyond development, covering evaluation strategies, CI/CD integration, prompt versioning, cloud scaling, and production monitoring and alerting.

 By the end, attendees will have the skills to take an AI agent from a local prototype to a fully monitored, production-ready system.

Read More →
View All Speakers

We use cookies essential for this site to function well. Please click to help us improve its usefulness with additional cookies. Learn about our use of cookies in our Privacy Policy & Cookies Policy.

Show details