Software Engineer, Enterprise AI Platform

OpenAISan Francisco, CA
$230,000 - $385,000

About The Position

The Enterprise Platform Technology (EPT) AI Pod builds AI-native internal apps, MCP connectors, multi-agent workflows, and reusable platform capabilities across Finance, People, and GTM. As an Enterprise Applied AI Engineer, you will build internal apps for enterprise operations and the shared platform components those apps run on. This includes MCP connectors, multi-agent orchestration, data architecture, evals, monitoring, auditability, and governance. We’re looking for a hands-on engineer who is strong in Python, system design, enterprise integrations, data architecture, and applied AI systems. You should be excited to turn ambiguous business workflows into reliable internal products and shared infrastructure.

Requirements

  • Strong Python engineering skills for backend services, MCP connectors, agent/tool workflows, eval harnesses, and data ingestion jobs
  • Strong system design skills across shared infrastructure, app architecture, reliability, and scaling
  • Experience building internal apps, backend services, APIs, workflow systems, or integration platforms
  • Understand enterprise systems, including controls, approvals, auditability, compliance, and permissions
  • Practical AI systems experience with RAG, evals, monitoring, MCP/tool use, structured outputs, or multi-agent workflows
  • Strong data architecture fundamentals, including ingestion, modeling, quality, lineage, and governance
  • Communicate clearly with technical stakeholders, system owners, and business owners
  • Take high ownership in ambiguous, cross-functional environments

Responsibilities

  • Build internal apps for enterprise operations across Finance, People, and GTM
  • Build MCP connectors and enterprise integrations with strong auth, permissions, idempotency, retries, and rate-limit handling
  • Design end-to-end multi-agent workflows with tool routing, human approvals, audit trails, and safe action boundaries
  • Design data architecture for operational AI systems, including ingestion, schemas, quality checks, lineage, and governance
  • Build evals, monitoring, metrics, and regression tests for agentic workflows
  • Create reusable infrastructure, patterns, and components that other enterprise teams can build on
  • Partner with system owners and business owners to turn messy enterprise workflows into reliable internal products
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service