Senior AI Builder

Replit Replit · Enterprise · Foster City, CA · Engineering

This role involves designing, architecting, and shipping AI-powered internal platforms that automate and improve operational processes across various departments of a fast-scaling company. The focus is on building agentic systems that incorporate LLMs, prompt engineering, tool use, RAG, and custom evaluation frameworks, with a strong emphasis on business understanding and end-to-end ownership of shipped software.

What you'd actually do

  1. Design, architect, and ship custom AI-powered internal platforms that serve specific operational needs across Replit’s functional departments, including but not limited to People Operations, Customer Support, Sales, Recruiting, Marketing, Finance, and Executive Operations.
  2. Translate ambiguous, often non-technical business requirements into technical specifications, system architectures, and shipped software products.
  3. Own platform development end-to-end, including front-end interfaces, back-end services, data models, third-party integrations, and AI model orchestration.
  4. Architect multi-stage AI pipelines incorporating large language models, including prompt engineering, tool-call architecture, structured output generation, retrieval-augmented generation, and agentic workflows.
  5. Conduct model selection across multiple frontier and open-source providers, evaluating models against cost per query, latency, output quality, reliability, and task-specific performance.

Skills

Required

  • Designing, architecting, and shipping AI-powered internal platforms
  • Translating ambiguous business requirements into technical specifications
  • End-to-end platform development
  • Architecting multi-stage AI pipelines
  • Prompt engineering
  • Tool-call architecture
  • Retrieval-augmented generation (RAG)
  • Agentic workflows
  • Model selection and evaluation
  • Cost and performance optimization for AI systems
  • Designing and implementing evaluation frameworks for AI features
  • Integrating with third-party platforms
  • Production operations and reliability
  • Business understanding and stakeholder partnership
  • Experience running own business or working on fast-scaling startup

Nice to have

  • Experience with enterprise HR platforms, support ticketing systems, CRM platforms, applicant tracking systems, project management tools, and identity providers.

What the JD emphasized

  • ship AI-powered internal platforms
  • ship custom software
  • ship the software that fixes it
  • ship before it is comfortable
  • own an outcome rather than a ticket
  • ship software products
  • shipped software
  • shipped platforms
  • shipped platforms

Other signals

  • AI-powered internal platforms
  • multi-stage AI pipelines
  • agentic workflows
  • model selection
  • evaluation frameworks
  • optimize AI systems for cost and performance
  • ship software that fixes it
  • own platform development end-to-end