Rootconf submissions for technical reviews

Topics

• AI infrastructure and operations

  • GPU Computing

    • Multi-GPU scaling optimization techniques
    • Memory optimization for large-scale training
    • Distributed training and inference architectures
    • Production deployment strategies

  • MLOps

    • Inference optimization techniques
    • Deployment and Inference techniques on edge devices
    • Model performance monitoring at scale
    • Standardized deployment practices

• CI/CD:

  • Case studies of CI/CD
  • Advances in CI/CD pipeline automation, including use of new tools and techniques to streamline deployments and reduce the time to market

• Core OS engineering

• Distributed systems

  • Testing for distributed systems

• Cloud security

• Container orchestration

• Deployment architecture of control plane plus data plane - why your organization adopted this approach.

• Detection engineering - detecting security issues and vulnerabilities in production

• Experience reports from using open source and proprietary tools for security

• Databases in production, including:

  • Why and how you arrived at the choice of which database to use?
  • Comparison of choices; trade-offs you have made for your architecture/use case

• FinOps

• High availability

• Hardware architecture and optimization

  • Performance engineering

    • Microarchitecture deep-dives for modern processors (AMD and Intel’s new processors have been in news quite a lot)
    • Performance debugging with system profilers such as perf, BPFTrace
    • Architecture-specific optimization case studies
    • Understanding hardware-software interactions

  • AI hardware evolution

    • GPU architecture and capabilities
    • Custom accelerator deployments
    • Cost-performance analysis for AI workloads
    • Hardware selection strategies

• Infrastructure engineering to manage and deploy complex systems

• Kubernetes in production, with focus on real-world experiences and lessons from running Kubernetes in production,

  • Best practices for scaling
  • k8s security
  • k8s troubleshooting
  • Getting started with k8s, including technical challenges and/or decision challenges

• Incident management, including:

  • Case studies of how you/your team did it
  • Documenting incident - how your team and you do it
  • Tools used for incident management and reporting
  • Root cause analysis

• Multi-cloud and hybrid cloud strategies, including:

  • Case studies of managing and optimizing multi-cloud and hybrid cloud environments
  • Interoperability challenges and wins
  • Cost management
  • Security
  • Multi-cloud strategies to avoid vendor lock-in and improve redundancy
  • Complexity in management and security

• Observability, including:

• Best practices for observability in modern applications
• Tools and techniques used for tracking what kind of metrics
• Logging
• Tracing to gain insights into system performance and reliability

• Reliability

• Resiliency, including:

• Techniques for building and maintaining resilient systems
• Chaos engineering - experience reports
• Fault tolerance
• Disaster recovery planning

• Securing systems running in production - incorporating security practices earlier in the software development lifecycle, commonly referred to as “shifting left” in DevSecOps

• Security for AI systems - tools, case studies.

• Serverless architectures: costs, benefits (such as reducing operational overhead) and challenges (such as cold starts and monitoring).

• AI security products - experience reports

• Software delivery management

• Software architecture, including:

• Decision journeys
• Case studies
• Failure stories

• System Internals for SRE and performance

  • Database Systems

    • Query execution and optimization
      • Storage engine internals
      • Performance tuning stories
      • High-throughput transaction processing
      • Vector databases: algorithms, internals, or performance

  • Programming language internals for better Observability and building high performance systems

    • New performance related changes and features in languages such as Python, Java, Rust
    • Runtime optimization techniques
    • Memory management patterns
    • Concurrency and parallelism
    • System-level programming languages: Rust, Zig, Mojo

  • Linux Internals

    • New features:
    • eBPF for system observability
    • Custom scheduling with sched_ext
    • io_uring developments and capabilities

• Security:

  • Speculative execution vulnerabilities and their impact on systems performance

• Testing and validation

  • Distributed Systems Testing
  • Deterministic Simulation Testing
  • Fault injection and chaos engineering

• Workflow management using Temporal