6 min readDevelopmentFeatured
Evaluating Tool-Calling Accuracy
Explore how to measure function call accuracy and build effective error taxonomies for evaluating LLM tool-use performance.
All tags
Tag
Ml Engineering
Read 6 articles on Ml Engineering by Ashish Srivastava — practical guides covering implementation patterns, security, and production lessons.
6 posts
6 min readDevelopmentFeatured
Building a Golden Dataset From Production Traffic
Learn how to extract, sample, and label production traffic to build a reliable golden dataset for evaluating large language models in production environments.
Part 2 · LLM Evaluation Engineering
6 min readDevelopmentFeatured
Knowledge Distillation: Logits, Sequences, and Rationales
A technical overview of knowledge distillation methods, covering logits, sequences, and rationales to help ML engineers optimize model performance.
Part 2 · Small Models & Distillation
6 min readDevelopmentFeatured
Agentic RAG: From Static Pipelines to Adaptive Retrieval
Static pipelines are limiting. Learn how agentic retrieval, adaptive strategies, and tool use transform RAG for ML engineers and architects.
Part 1 · Agentic RAG Patterns
8 min readDevelopmentFeatured
Reading a GPU Spec Sheet: FLOPs, Bandwidth, and What Binds You
Stop guessing which GPU fits your workload. Learn to read spec sheets by understanding the relationship between compute power, memory bandwidth, and arithmetic intensity.
Part 1 · GPU Economics for AI Teams
6 min readDevelopmentFeatured
Your First Production Inference Server: A Complete Walkthrough
Learn to deploy a reliable inference server with Docker, implementing streaming responses and health checks for production readiness.
Part 8 · LLM Inference from Scratch