Built ML Models → Shipped LLM RAG at 92% Helpfulness: ML Bullets
Free · No signup · Recruiter-reviewed
Three nouns added that only an ML engineer who shipped this could know: the architecture (RAG on GPT-5.4), the eval metric (helpful rating), and the live traffic volume (280k convos in 8 weeks). The original sentence could describe any data role.
Shipped a RAG-based help assistant on top of GPT-5.4, lifting 'helpful' rating from 71% to 92% over 8 weeks of online eval across 280k conversations.
What changed and why
- Specify the architecture (RAG, fine-tune, distillation) — recruiters in 2026 expect ML eng candidates to name the pattern.
- Eval metric > model accuracy. Helpfulness, win-rate, NPS-delta and downstream conversion beat 'accuracy improved 5%' every time.
- Quote the live-traffic volume (280k conversations) so the result is statistically defensible — single-digit % wins on tiny samples are noise.
- Time window (8 weeks) prevents a recruiter from assuming you A/B'd for a day and called it done.
Recruiter perspective
“Named the model, named the eval, quoted the sample size. This candidate has shipped LLM eng, not just notebook ML.”
Related rewrites
Optimized Performance → Cut p99 280ms: Backend Bullets With Proof
Replaced two filler nouns ('performance', 'overall system efficiency') with the actual query path, the actual percentile, and the actual remediation. Senior engineers always speak in p99 / p95, never 'overall efficiency'.
Built Models → +£1.1M ARR From Churn Model: Data Science Bullets
Three vague nouns ('predictive models', 'customer outcomes', 'business strategy') replaced with the algorithm class, AUC, the operational workflow it landed in, the save-rate delta, and the £ARR attribution. Data scientists who can quote ARR attribution outrank those who only quote AUC.
Built Pipelines → Cut Snowflake £62k/Yr: Data Eng Bullets
Replaced 'scalable pipelines' (a phrase that means nothing in 2026) with the warehouse name, the £-saving, the pipeline count, the specific dbt patterns, and the warehouse-sizing detail. Data eng is graded on cost + reliability — quote both.