Founding AI Applications Engineer

Job Description

• Architect & ship AI agent services - Design Python/TypeScript microservices that orchestrate LLMs (OpenAI, Claude, open-source), vector databases, and payment APIs.
• Automate merchant-specific tuning - Build pipelines that ingest merchant data (e.g. reviews, support transcripts, transaction logs) to fine-tune or RAG-augment models automatically.
  
  
• Create self-serve tooling for Ops - Develop chat-based or low-code UIs that let our ops team teach and monitor agents — no code required.
  
  
• Own the AI / ML lifecycle - Handle model versioning, evaluation (online/offline), monitoring, rollback, and performance/cost optimization.
  
  
• Move from zero one scale - Stand up lightweight infrastructure today; scale it to serve thousands of merchants tomorrow.
  
  
• Set the bar for engineering excellence - Establish high standards for code quality, system design, and team culture.
  
  Mentor early team members.
  
  

Requirements

• Proven 10× builder with 5–10+ years of experience shipping production systems — and a continued love for hands-on coding.
  
  
• LLM experience in production, including building or fine-tuning models with OpenAI, Claude, Llama 3, or similar, and shipping at least one LLM-powered feature.
  
  
• Strong data intuition, with experience designing labeling strategies, feedback loops, and evaluation harnesses to maintain model quality.
  
  
• Service-oriented engineering mindset, writing clean, tested Python (or similar) and building APIs that other engineers enjoy using.
  
  
• Bias toward automation, with a focus on building agents and workflow tools that eliminate repetitive tasks.
  
  
• Excellent collaboration and communication skills to work effectively with cross-functional teams.
  
  
• Experience in payments, risk, or blockchain; infra-as-code tools like Terraform or Pulumi; GPU cost optimization; or TypeScript/React for internal tools is a bonus.