Carthi P Senior ML Engineer

Articles

Notes on ML engineering, data pipelines, inference optimisation, and things I've learned shipping models to production.

  • Data Engineering · 1
  • ETL · 1
  • Inference · 1
  • LLM · 1
  • MLOps · 1
  • ONNX · 1
  • PySpark · 1
  • PyTorch · 1
  • Python · 1
  • RAG · 1
  • Vector Search · 1

Shrinking a PyTorch Model's Memory Footprint with ONNX

4 min read

A walkthrough of exporting PyTorch models to ONNX for deployment — what actually gets smaller, what doesn't, and the export gotchas worth knowing before you ship.

  • PyTorch
  • ONNX
  • Inference
  • MLOps

What Actually Breaks in a Production RAG Pipeline

4 min read

Retrieval quality, not generation quality, is where enterprise RAG systems fail. Notes from building ingestion, embedding and vector search for enterprise document corpora.

  • RAG
  • Vector Search
  • LLM
  • Python

Designing a PySpark Pipeline That Survives Schema Drift

3 min read

Third-party data changes shape without telling you. Notes on building ingestion that fails loudly at the boundary instead of silently three tables downstream.

  • PySpark
  • Data Engineering
  • ETL