AI Cost Optimisation Gateway MVP

I need an experienced backend engineer to build a pilot-ready MVP of an AI cost-optimisation gateway for UK companies, built on LiteLLM. It sits between clients’ apps and OpenAI, Anthropic and Google to cut AI costs and protect personal data.

Stack: LiteLLM (single gateway) with Python hooks, TypeScript/NestJS services, Next.js dashboards, PostgreSQL, Redis, Docker, AWS London (two availability zones).

Scope: per-client keys, budgets and spend tracking; PII masking with Presidio plus UK detectors (NI, NHS with checksum, postcodes); exact and semantic caching isolated per client; retries and backup models; savings ledger with shadow-mode baseline; basic batch API routing, cache-hit diagnostics and spend-spike alerts; dashboard and monthly savings statement; audit log, tests and docs.

Fixed-price milestones paid on acceptance tests, code in my company GitHub from day one. Target: pilot-ready by mid-December.

Please share a gateway or proxy project you’ve built (not just a chatbot) and your experience with LiteLLM, Presidio and AWS. Nice to have: UK GDPR awareness and experience with provider batch APIs and prompt caching. Shortlisted candidates sign a short NDA before seeing the full brief, and the best one or two may do a small paid trial (the UK PII detectors). Please include your price per milestone, weekly availability and start date. Weekly progress updates expected.