Senior Software Engineer (AI)

Arcadia; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Arcadia, a high-growth startup, is hiring a Senior Software Engineer to join the founding team. You will own full stack architecture across frontend and backend, working with TypeScript/React on the frontend and Python on the backend, directly with LLMs to measure model behavior.

You'll build evaluation frameworks, architect AI agent workflows, and influence product features and roadmaps in a fast-paced, autonomous environment.

Qualifications

• Strong full stack experience in production environments.
• Hands-on with LLMs, evals, RAG, or applied AI product work.

Responsibilities

• Own full stack architecture decisions from day one, spanning frontend to backend.
• Design and build systems that evaluate and quantify LLM perception of structured and unstructured data.
• Build and orchestrate agentic workflows for automated evaluation, data processing, and model behavior analysis.
• Work directly with LLMs and model outputs to build novel measurement and evaluation frameworks.
• Ship product end to end, from data pipelines to user-facing interfaces.

Skills

TypeScript

React

Python

Full stack

LLMs

Job description

A high-growth startup is building the infrastructure to measure how LLMs actually perceive and process data, giving teams visibility into model behavior that's historically been a black box. They're hiring a Senior Software Engineer to join the founding team for a true 0→1 opportunity, architecting the core product alongside a small, technical founding group.

You'll move fluidly across frontend, backend, and applied AI, including building and orchestrating AI agents end to end, with real ownership in a fast-paced, autonomous environment.

The Stack

TypeScript/React on the frontend, Python on the backend. You'll be working directly with LLMs and model outputs, building the evaluation and measurement frameworks from scratch.

What You'll Do

• Own full stack architecture decisions from day one, spanning frontend to backend
• Design and build systems that evaluate and quantify LLM perception of structured and unstructured data
• Build and orchestrate agentic workflows for automated evaluation, data processing, and model behavior analysis
• Work directly with LLMs and model outputs to build novel measurement and evaluation frameworks
• Ship product end to end, from data pipelines to user-facing interfaces
• Set technical standards and engineering culture as one of the first hires
• Work directly with founders and have real say in product features, roadmap, and technical decisions

What Makes You a Fit

• Strong full stack experience with TypeScript, React, and Python in production environments
• Hands-on experience building with or around LLMs, whether that's evals, fine-tuning, RAG, or applied AI product work
• Founding engineer, founder, or very early-stage startup experience, comfortable with ambiguity and moving/shipping fast
• Genuinely excited to be hands-on at every layer of the stack

Why This Role

One of the first engineering hires at a high-growth, well-backed startup tackling a problem that's only getting more critical as LLMs get embedded everywhere. Huge ownership, huge technical surface area, and a real seat at the table for foundational product decisions.