Skip to main content
RM

Writer

Ravi Menon

Principal AI Engineer

Previously ML platform engineering at scale

Ravi builds the applied AI systems we ship: retrieval pipelines, evaluation harnesses and the guardrails that keep a model useful once real users reach it. He writes about the engineering that decides whether an AI feature survives production.

  • LLM evaluation
  • Retrieval-augmented generation
  • Prompt engineering
  • AI cost modelling
4
Articles
4
Expertise
  • Syntax-highlighted source code on a dark editor screen
    AI Engineering

    RAG that actually retrieves: fix the retrieval layer first

    Most retrieval-augmented generation problems are retrieval problems wearing a generation costume. Fix chunking, hybrid search and reranking before you touch the prompt.

    RMRavi Menon2 min read
  • The letters A and I rendered above a circuit-patterned surface
    AI Engineering

    Evaluating LLM features before you ship them

    Most AI features fail in production because nobody built a way to tell whether a prompt change made things better or worse. Here is the evaluation harness we build first.

    RMRavi Menon2 min read
  • Small humanoid robot seated on a wooden bench
    AI Engineering

    What an AI agent actually costs per completed task

    Token pricing is not the interesting number. Cost per successfully completed task, including retries and human escalation, is the one that decides whether an agent ships.

    RMRavi Menon2 min read
  • Close-up of a circuit board with processors and surface-mounted components
    AI Engineering

    Chatbot guardrails that hold up in front of customers

    Refusals, scope limits and escalation are product decisions, not prompt lines. Here is the guardrail stack we ship on customer-facing assistants.

    RMRavi Menon1 min read

ExploreKeep exploring

Related pages

Guides

Subscribe Newsletter

Practical playbooks on AI, product engineering, growth marketing and creator campaigns. One email a month, no filler.