raji muhammed robiu

ai/llm engineer. computational linguistics degree, shipped products on free-tier infrastructure: multi-provider inference routing, self-updating data pipelines, and llm-as-decision systems where the model is one component among several.

working on now: running a 30-day public eval of a paper-mode crypto signal engine · launching flippy cloud (hosted version of my inference router) · building the @promptcracka build-in-public channel.

what i build

flippy

147 passing tests

every llm provider rate-limits or goes down eventually, and apps built on one provider stop with it. flippy is an inference router that fails over across four providers automatically, plus a unified hub for chat, rag, tool-calling, vision, tts and stt.

repo & stack → pythonlitellm routerpytest

what i learned: failover is easy to write and hard to test — the value is in simulating provider failures before they happen in production.

just-hired

refreshes every 2 hours, live in production

job boards serve stale postings, so searchers waste hours applying to filled roles. just-hired shows only direct-employer postings from the last 12 hours, fetched by a cloudflare worker (which gets past job bank's datacenter-ip block where github actions couldn't) and redeployed automatically.

repo & stack → cloudflare workernetlify apicron

what i learned: egress location matters more than code quality when a source blocks datacenter ips — pick the runtime the source trusts.

dont-get-rekt

44 parser tests · 30-day live-mode eval gated behind a flag

an llm voting real money on its own judgment is one bad prompt away from losing it. this is a paper-mode crypto signal engine: the pipeline computes every metric first, then a free-tier llm casts a structured buy/skip vote per token — the model judges inputs it can't fabricate, and the engine can override it.

repo & stack → structured outputpaper tradingfeature flags

what i learned: keep the model as judge, never as source of truth — and gate anything risky behind an explicit opt-in flag.

you-are-fired

hard send caps + opt-out enforcement in code

cold outreach usually claims too much and proves too little. this system finds one measurable defect per prospect, prices the fix, and drafts one email at a time with evidence the recipient can verify in twenty seconds. send limits and unsubscribe handling are enforced by the pipeline, not by discipline.

repo & stack → smtpdnsrate limiting

what i learned: safety rules that live in config get ignored; rules enforced in code survive pressure.

background

  • b.a. in english language (computational linguistics focus) — final-year project applied ai analysis to linguistic data. this is why prompt design and structured output are first-class concerns in everything above.
  • fortinet nse 1–3 certified. network security fundamentals through fortigate configuration.
  • cisco cyberops associate certified. security operations, intrusion analysis, incident response.

how to reach me