Drimva

Standard Bots

Staff Software Engineer

$215K–$250K

New York City, NY · Hybrid · Staff · Full-time · Posted Jul 13, 2026

Experience
8+ years of professional software engineering, including hands-on AI work; qualifying AI experience may include shipping an LLM-powered product, building model evaluation systems, or production data work for AI/ML.

About the job

Own and ship an LLM-powered robot-programming agent and the vertical applications it drives, taking them from demo to reliable customer-facing products.

What you'll do

  • Set the product and technical direction for the agent and vertical applications, including interaction design, guardrails, and stable interfaces to robot platform APIs.
  • Lead cross-functional delivery and production hardening, including reliability, secure key management, offline modes, and release engineering.
  • Build agent evaluation systems and quality metrics, turn customer failures into regression cases, and mentor engineers.

What they ask for

  • 8+ years of professional software engineering experience, including hands-on AI work such as shipping an LLM-powered product, building model evaluation systems, or production data work for AI/ML.
  • Fluency in agent loops and tool calling, prompt and context management, structured output, model selection and fallbacks, and token/latency economics.
  • Experience building evaluation datasets, harnesses, or regression gates for nondeterministic systems and using them for launch decisions.
  • Product ownership involving direct user engagement and decisions about what to build.

Nice to have

  • TypeScript/Node.js fluency; range across React, Python, C++, and Kubernetes.
  • Experience serving operational, domain-heavy users, such as in manufacturing, logistics, or field operations.

Pay

$215,000 to $250,000 USD base salary

Tools

TypeScript/Node.js, React, Python, C++, Kubernetes

AI focus

Build and productize an LLM-powered agent for programming industrial robots through conversation; develop agent evaluations, quality metrics, and release gates. This is not a model-training research role.

Model-written summary · the original posting is authoritative

First seen Oct 10, 2026 · Last verified Nov 4, 2026 (UTC)