AI Engineer

The BuildClub; United States; Remote; USD 140,000 - 210,000; Full time

Job summary

The BuildClub is seeking a senior software engineer to ship AI-driven client workflows in a fully remote role across the United States. You’ll own multi-step agent design, tool integrations, and evaluation harnesses, ensuring observable, reliable production systems.

You’ll mentor junior engineers, establish robust patterns, and collaborate with clients to implement production-grade LLM solutions that stay ahead of drift and complexity.

Qualifications

• Five-plus years building production systems, including 18+ months with LLMs and agent frameworks.
• Strong Python and TypeScript; comfort with cloud (AWS or GCP), containers, and CI/CD.
• Experience with AI evaluation, prompt engineering, and model-provider tradeoffs.
• Ability to ship simple, observable solutions over clever ones.
• Excellent written communication for explaining technical decisions to non-technical clients.

Responsibilities

• Design and implement multi-step AI agents that run inside real client workflows.
• Integrate with client systems (Salesforce, NetSuite, SharePoint, custom databases).
• Build evaluation and monitoring to detect agent drift and ensure reliability.
• Own production reliability of shipped systems.
• Mentor junior engineers and establish patterns the team follows.

Skills

Python

TypeScript

Cloud (AWS or GCP)

CI/CD

AI evaluation / prompt engineering

Observability

Communication

Tools

Docker

Job description

Full-time · RemoteShip the technical systems behind BuildClub's digital workforce — agents, integrations, evaluations, and the plumbing that makes them production-grade.You'll be one of the senior engineers responsible for everything that turns an LLM into a working part of a client's operation: agent design, tool integration, evaluation harnesses, observability, and the boring infrastructure that keeps it running at 2 AM.

What you’ll do

• Design and implement multi-step AI agents that run inside real client workflows
• Integrate with the systems clients actually use — Salesforce, NetSuite, SharePoint, custom databases, and worse
• Build evaluation and monitoring so we know when an agent is drifting before the client does
• Own the production reliability of the systems you ship
• Mentor junior engineers and write the patterns the rest of the team follows

What you bring

• Five-plus years building production systems, including at least 18 months working hands-on with LLMs and agent frameworks
• Strong Python and TypeScript; comfort across cloud (AWS or GCP), containers, and CI/CD
• Real experience with AI evaluation, prompt engineering, and the tradeoffs between model providers
• The instinct to ship something simple and observable before something clever
• Written communication strong enough to explain technical decisions to a non-technical client