Anuj Tyagi
Senior Site Reliability Engineer - AI
Middletown, Delaware, United States
Actions
Anuj is Senior SRE with a decade of experience in Site Reliability, AI workloads, Production Engineering, DevOps, Cloud native enthusiast.
Links
Area of Expertise
Topics
SRE Playbook for LLMs and AI Agents: Observability, Scaling, and Reliability
AI agents are hitting production faster than SRE practices can keep up. Traditional RED metrics don't capture reasoning loops, context window exhaustion, or LLM provider throttling and your existing HPA won't scale what it can't measure. This talk delivers the playbook SREs need: which metrics to monitor for LLMs and AI agents, how to define meaningful SLOs for non-deterministic workloads, and how to autoscale agent workers using KEDA with custom Prometheus metrics built from real-world experience operating AI workloads on Kubernetes at scale.
Building Guardrails for LLMs
A real-world case study on building SentinelGuard, a production-ready LLM security framework with 32 scanners, PII protection, adversarial defense, and embedding guardrails and the engineering trade-offs behind making GenAI systems safe at scale.
How I developed custom Terraform provider
This talk introduces useful for anyone to develop a custom Terraform provider, enabling developers to extend Terraform’s functionality to manage non-standard or unique infrastructure resources.
Part of this talk, I want to share share my experience and challenges how I developed Terraform provider to manage database Indexes for MongoDB.
By following same workflow, one can develop a provider in Go/Golang for any application.
The session covers essential concepts, provider architecture, and a step-by-step guide to implementation using Go/Golang. Attendees will learn to design and build a custom provider for any application or service, bridging the gap between Terraform and custom APIs or resources.
How I build custom Terraform provider
A deep dive into building custom Terraform providers to manage non-standard resources—sharing how I built one for database index management.
When I did my search online and found no stable provide available to manage MongoDB index, I decided to develop my own. Part of this talk, I want to share experience and challenges to develop Terraform provider to manage for MongoDB provider.
PlatformCon 2026 Sessionize Event Upcoming
HashiTalk 2026
The HashiCorp practitioner community is driven by users around the globe,
executing use cases that embody best practices, showcase various patterns,
and that test the edge use cases of HashiCorp tools.
DevOps Days Philadelphia
Devopsdays is a worldwide series of technical conferences covering topics of software development, IT infrastructure operations, and the intersection between them.
HashiConf 2025 Sessionize Event
CloudX 2025 Sessionize Event
DevOps Days Baltimore
DevOpsDays Baltimore brings development, operations, InfoSec, AI, Quality Assurance, IT management, and leadership together to discuss the culture and tools to make better organizations and products. The 2025 event is in a new location, offering an intimate setting that fosters deeper networking, personalized interactions, and an immersive experience where every conversation counts.
Anuj Tyagi
Senior Site Reliability Engineer - AI
Middletown, Delaware, 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