Skip to main content

Boom

AI Engineer

Austin Texas$120k–$200kfulltimemidAdded 1 month ago

About this role

Boom is seeking an AI Engineer to build production-grade customer-facing AI agents and internal productivity tools for a fintech platform serving renters and property managers. You'll own the full AI stack—from prompts and tools to evals and observability—working closely with founders and leadership in Austin to ship real revenue-bearing workflows.

What you'll do

  • Develop and deploy production AI features and agents across Boom's customer-facing products
  • Build internal AI productivity tools and automations for engineering, operations, and sales teams
  • Own the complete agent infrastructure including prompts, tools, memory, retrieval, and orchestration
  • Design evaluation frameworks and feedback loops to safely improve agents without regressions
  • Partner with product and leadership to identify and prioritize AI initiatives
  • Contribute to engineering culture and hiring decisions

What they're looking for

  • 5+ years web development experience
  • 1-2 years building production LLM features or agents
  • Hands-on experience with Anthropic and OpenAI APIs
  • Agent architecture patterns (tool use, structured outputs, RAG, multi-step planning)
  • Evaluation and testing methodologies for LLM systems
  • Product judgment for LLM applications
  • Observability and monitoring
  • System design and scaling
Apply with Autofill

Opens the application — the Jobs AI extension fills it for you. Set up autofill

Opens the official application on the employer’s site. No login required.

Boom

Boom builds a financial services platform serving renters and property managers, offering rental-related financial products and tools. The company is hiring QA Engineers, AI Engineers, and Security Engineers to scale product quality, develop AI-powered customer and internal tools, and establish security practices across their platform.

View all jobs at Boom

Likely interview questions

  • Walk us through a production LLM feature or agent you built end-to-end. How did you approach evals, and what's the difference between what you shipped versus what you demoed?
  • Tell us about a time you had to decide between an AI solution and deterministic logic. What factors drove that decision, and how did you handle the trade-offs?
Unlock all 7 questions free — and practice them live →