I will audit and optimize your llm API infrastructure

Production LLM systems waste 30-60% of their API spend on the wrong model, the wrong routing strategy, or the wrong prompt structure.

I'm a Senior ML Engineer who builds and operates LLM infrastructure for an enterprise SaaS, Kubernetes-native inference, multi-provider routing, and RAG systems running at scale. On the side, I help smaller teams audit and tighten their setups before they scale, and the costs become catastrophic.

What you get:

• Cost analysis: where your API spend is going and where it's leaking
• Architecture review: routing, fallback, caching, observability gaps
• Prompt audit: token usage, structure, output stability
• Security check: auth, rate limiting, PII handling, prompt injection vectors
• Prioritized recommendations with effort/impact scoring

Who this is for:

• Startups running OpenAI/Anthropic in production and seeing the bills climb
• Teams about to scale their LLM features who want to get the foundation right
• Founders who want a senior eye on their AI system before raising or shipping

What I'll need from you:

• Read-only access to your code/repo
• 2-3 sample prompt traces or logs
• A 15-min kickoff call to understand goals

Message me before so we can confirm scope.