Quick 30min Interview: AI Developers / Engineers Using High LLM Token Volumes

I am conducting interviews with developers, engineers, founders, or product teams who use LLMs or AI agents heavily in day-to-day product development. The goal is to understand how teams currently manage, monitor, and optimize token usage, inference cost, latency, and model selection. I would like to learn about: - How you use LLMs or AI agents in your product/workflow - Where most of your token usage or AI cost comes from - What tools or processes you use to track and reduce token spend - How you choose between models or providers - What pain points still remain unsolved in your current workflow It is a plus if you have experience with tools such as OpenRouter, Portkey, LiteLLM, LightLLM, Helicone, LangSmith, Langfuse, or similar AI gateway, routing, or observability tools. I am looking to learn from your practical experience and understand real pain points around AI token and inference cost optimization. If there is a strong fit, there may also be an opportunity to continue collaborating or work together on this project beyond the initial interview. Ideal Candidate Software engineer, AI engineer, ML engineer, founder, or product builder who uses LLM APIs or AI agents frequently.