Can you give me an email to reach out to you at? My company may need an intern/Junior here soon. I'd be happy to take a look at his resume.

Fully remote, Full stack .NET in addition to AI/Python/data-science work

Honestly, that is way too much for a junior.

I'd side-eye that list as senior .NET dev full stack.

You're asking one person to do frontend/js/css, backend/databases/Redis/MQ, and Python with all that math behind data-science, but i doubt he can understand and review all of this

Of course I wouldn't give all that to a Junior! It's just what they could expect to work with if they stayed long term.

dverespey@gmail.com is mine. In my profile as well.

$MY_STARTUP does — something — similar. I — love — that — you — say — you'll — do — this — in — a — week, — and — then — a — two — week — warranty? What — are — you.. replacing — an — engine? — Gotta — keep — that — head-gasket sealed — tight.

/s Isn't this just called a consultancy with a super short contract term? How are you actually going to unscrew anything in one week?

> Chain-of-thought is crippled by structured outputs

I don't know if this is true. Libraries such as Pydantic AI and I would assume the model provider SDKs stream different events. If COT is needed then a <think> section would be emitted and then later the structured response would occur when the model begins its final response.

Structured outputs can be quite reliable if used correctly. For example, I designed an AST structure that allows me to reliably generate SQL. The model has tools to inspect data-points, view their value distributions (quartiles, medians, etc). Then once I get the AST structure back I can perform semantic validation easily (just walk the tree like a compiler). Once semantic validation passes (or forces a re-prompt with the error), I can just walk the tree again to generate SQL. This helps me reliably generate SQL where I know it won't fail during execution, and have a lot of control over what data-points are used together, and ensuring valid values are used for them.

I think the trick is just generating the right schema to model your problem, and understanding the depth of an answer that might come back.