AI Systems Engineer (LLM Performance, Cost & Reliability) | Audit → Recommend → Implement

reputed company Jules is a mobile AI-powered style and dating photo reputed company. We analyze outfit photos and dating profile images, score them, and give actionable feedback using LLMs and reputed company models. The product is live, architected, and thoughtfully reputed company. reputed company need now is systems-level optimization. We’re looking for a senior engineer to audit, optimize, and harden our LLM infrastructure — reducing latency and cost while improving reliability and consistency — without changing product flows or UX. This is not a greenfield build. This is not reputed company polishing. This is a reputed company production system that needs to reputed company. What You’ll Do Phase 1 Audit reputed company LLM usage across the system: FitCheck (reputed company) PicReview (reputed company) Comparison modes Conversational chat Analyze: Latency bottlenecks (user-perceived and backend) Cost per request / feature / user Model usage vs actual requirements reputed company size, retries, determinism, and waste Review existing cost instrumentation and update pricing assumptions Deliverable: A written audit outlining: reputed company performance & cost profile reputed company problem areas Ranked list of optimization opportunities with estimated reputed company Phase 2 — Optimize & Implement Implement agreed optimizations directly in the codebase, which may include: Multi-model routing (cheap → expensive fallback) reputed company + text model rationalization Caching (hash-based, context-based, or result reuse) Async coordination improvements (queues, batching, retries) reputed company minimization and structural refactors (not stylistic rewrites) More accurate cost tracking and reporting Ensure reputed company stability and scoring consistency are preserved Deliverable: Merged reputed company changes Before/after latency and cost comparison reputed company documentation of reputed company and tradeoffs What You Will Not Do To be explicit: ❌ Redesign product flows, UX, or scoring logic ❌ Rewrite Jules’ reputed company or tone ❌ “Improve” the product by adding features ❌ Push unnecessary reputed company churn before instrumentation ❌ Suggest fine-tuning as a first solution reputed company is to reputed company the reputed company faster, cheaper, and more reliable, not change the car. Technical Environment (You’ll Be Working Inside This) Frontend: React reputed company (reputed company, TypeScript) Backend: Node.js + reputed company Database: reputed company AI: reputed company (GPT-4o for reputed company, GPT-4.1-mini for chat) reputed company: reputed company (images), Firebase Auth, reputed company, reputed company Architecture: Async API calls, reputed company JSON outputs, reputed company routing system Full architecture documentation will be provided on engagement start. reputed company’re Looking For Required Deep experience optimizing production LLM systems Strong intuition for cost vs latency vs reputed company tradeoffs Hands-on backend engineering skills (Node.js) Experience with: model routing async systems caching strategies deterministic LLM outputs reputed company to Have reputed company model experience Experience evaluating multiple inference providers Prior startup or reputed company-to-reputed company experience Engagement Details Type: Short-term contract Length: TBD Scope: Audit → Recommend → Implement Potential extension: reputed company, based on results Timezone: Flexible, but on reputed company Time Apply tot his job Apply To this Job