Founding Applied AI Engineer
Role summary
This role focuses on building and deploying production-grade AI systems, including agentic AI, RAG pipelines, and LLM workloads. The engineer will be responsible for ensuring the reliability, safety, and integration of these systems into core product workflows. The position requires experience shipping AI to real users, deep familiarity with agents, RAG, and orchestration, Python development, and production ML/LLM operations. Experience in early-stage environments is crucial. Preferred qualifications include experience with orchestration frameworks like LangGraph or Temporal, vector databases, and secure systems like HIPAA/SOC-2 compliant environments.
Job Summary
You’ll build the next generation of production-grade AI systems—agents that reason, act, and operate reliably in messy, real-world environments. This role focuses on designing and deploying agentic AI, RAG pipelines, and LLM workloads in production, with an emphasis on reliability, safety, and integration into core product workflows.
Responsibilities
- Design and ship agentic AI systems
- Build RAG pipelines and tool-using agents
- Deploy and monitor LLM workloads in production
- Focus on evaluation, reliability, and safety
- Integrate AI into core product workflows
- Work closely with founders and customers
Requirements
Required Qualifications
- Experience shipping AI systems to real users
- Deep familiarity with agents, RAG, and orchestration
- Python-first development experience
- Production ML / LLM operations experience
- Comfort operating in early-stage environments
Preferred Qualifications
- Experience with LangGraph / Temporal / orchestration frameworks
- Vector databases
- HIPAA / SOC-2 compliant systems
- Terraform / Kubernetes
- Edge or real-time AI systems
Benefits
- Full-time position
- Location: San Francisco / New York
- Salary: $150k to $300k
- Role stage: Seed → Series B
This role is for a client of Weekday (not internal team)
