Cut Latency and Cost on a High-Volume Summarization Service
Overview
What this challenge is about.
Profile latency and cost logs, then benchmark four optimizations for a high-volume AI service and earn a verifiable certificate.
The scenario
The startup (~50 staff, ~1.5M MAU) currently spends ~USD 40k/month on LLM inference; a 30% cut is a board-level target.
The Brief
What you'll do, and what you'll demonstrate.
Cut LLM cost 30% and p95 latency to under 1.8 s on a news-summarization service without losing quality.
Earning criteria — what you'll demonstrate
- Profile LLM cost and latency distributions from real logs
- Apply prompt compression, model tiering, and caching as cost levers
- Calibrate LLM-as-judge against human ratings
- Communicate optimization trade-offs to product stakeholders
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Aligned coursework coming soon.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
- Cost Optimization
Apply cost optimization to solve real industry problems and demonstrate production-level capability.
- Latency Optimization
Apply latency optimization to solve real industry problems and demonstrate production-level capability.
- Prompt Compression
Apply prompt compression to solve real industry problems and demonstrate production-level capability.
- Model Tiering
Apply model tiering to solve real industry problems and demonstrate production-level capability.
- Response Caching
Apply response caching to solve real industry problems and demonstrate production-level capability.
- Llm Evaluation
Apply llm evaluation to solve real industry problems and demonstrate production-level capability.
Careers
Career paths this challenge builds toward
Completing this challenge demonstrates skills that transfer directly to these roles:
AI Engineer
Profiling, optimizing, and shipping cost/latency wins on a real LLM service is the day-to-day of AI engineers at scaling AI products.
This challenge sharpens
- cost-optimization
- latency-optimization
- prompt-compression
MLOps Engineer
Model tiering and caching at request-level is core MLOps work on inference platforms.
This challenge sharpens
- model-tiering
- response-caching
- cost-optimization
AI Product Manager
Owning the quality-vs-cost trade-off and the board-facing write-up is the AI PM's daily job.
This challenge sharpens
- cost-optimization
- llm-evaluation
- model-tiering