Personal Reflections & Tech Insights

Blogs

Building Safe LLM Agents in Production

LLM agents offer powerful automation, but their inherent unpredictability makes production deployments tricky. Architecting for reliability and safety is crucial to avoid surprises.

Graph Databases Boost AI Feature Engineering

Graph databases excel at modeling relationships, providing rich contextual features for AI models that tabular data often misses. Learn how leveraging graph structures can significantly enhance feature engineering.

Causality in Production AI Systems

Observing correlations in AI system behavior is easy. Understanding the underlying causes is much harder but essential for robust production systems and effective debugging.

Serving Fresh AI Features: The Real-time Store Connection

Real-time feature stores bridge streaming data with AI models, solving staleness and training-serving skew for low-latency predictions.

Idempotency Makes Retries Safe in Distributed Systems

Building reliable distributed systems means handling failures. Idempotency ensures operations can be retried without unintended side effects, making your system much more resilient.

Orchestrating LLM Workflows in Serverless

Building real-world LLM applications often means chaining multiple prompts, conditional logic, and retries. Serverless functions need orchestration to manage this state and complexity.

Scaling Reinforcement Learning in Production

Moving RL agents from research to production brings unique challenges. It's not just about the model, but the entire system around it.

Hierarchical Caching with Hierarchical Temporal Memory

Optimize AI model deployment with hierarchical caching and Hierarchical Temporal Memory.

CI/CD for Large-Scale AI Models

Streamlining the deployment of complex AI models using cloud-native buildpacks and GitOps