Tracking Longterm Health with Elasticsearch x AWS User Group Seattle

The Elastic Seattle User Group & AWS User Group Seattle (AWSUGSEA) are partnering for a joint meetup on Thursday, October 23rd. We'll have presentations from Justin Castilla (Sr. Developer Advocate at Elastic) Natalie Serebryakova (Staff Cloud Engineer at IN-N-OUT.CLOUD), followed by food, refreshments, and networking.

📅 Date & Time:
Thursday, October 23rd, from 5:30-7:30 pm PDT

📍Location:
AWS Skills Center (across the street from its former location at the Amazon Kiro building)

Amazon Oscar building
1007 Stewart St
2nd floor
Seattle, WA 98101

🚗 Parking:

• SpotHero - Book a parking spot in advance

🪧 Arrival Instructions:

• Guests will go upstairs to the AWS Skills Center on 2nd floor. It’s directly up the stairs or elevator or they can use escalator and just follow floor signage to navigate to the entrance.
• Check-in with our guest reception team and then be directed to the rooms. Even though the Skills Center closes at 5pm, they will be open for the user group.

💭Talk Abstracts:
Tracking Longterm Health with a Sympathetic Voice - Justin Castilla - Sr. Developer Advocate at Elastic

This talk will introduce developers to the Model Context Protocol (MCP) through a practical example that demonstrates how to build AI-powered applications that integrate Claude Desktop with external data sources like Elasticsearch. Attendees will learn core MCP concepts while exploring real-world implementation patterns like structured data validation, multi-step workflows, LLM-as-a-jury evaluation, and semantic search capabilities. Developers with basic Python and API experience will leave understanding how to create MCP servers that transform static data into interactive, AI-accessible resources, enabling new paradigms for user interaction in their own applications.

AWS EKS GPU Spot Recovery Operator for ML Workloads - Natalie Serebryakova - Staff Cloud Engineer at IN-N-OUT.CLOUD

In this session Natalie will be speaking about Kubernetes operator for AWS EKS that detects Spot interruptions on GPU nodes, triggers ML job checkpointing, and recovers training by rescheduling on available nodes. This I prepared with an idea to provide an interesting example of a repeatable workflow for maximizing GPU cost savings without losing progress on ML training jobs. The setup covered in this talk will include services AWS EventBridge, S3/EFS , IAM, and CloudWatch. Natalie will be presenting a live example to show node interruption handling, and seamless ML job recovery using my developed solution.