Composio

Member Technical Staff - Applied AI Engineer (US Timing)

Bangalore. Posted 2 months ago

The role

You will build agentic workflows and tool-using agents to automate support functions. You will work directly with customers to turn repeated problems into product capabilities, workflows, or tools.

What you will do

  • Build agentic workflows for intake, classification, diagnosis, and remediation
  • Build tool-using agents to inspect runs, logs, and auth state
  • Create eval suites for diagnostic correctness and resolution quality
  • Develop human-in-the-loop systems for ownership and approvals
  • Build observability, memory, and feedback loops for agents
  • Implement product improvements to remove customer issues
  • Own hard issues end to end from reproduction to shipping
  • Partner with Support, FDE, Product, and Engineering
  • Move prototypes to reliable production workflows
  • Use frontier models and coding agents to multiply engineering output

Required qualifications

  • 2–4 years of professional software engineering experience
  • Built production systems with language models, tool calling, retrieval, structured outputs, multi-step workflows, or agent memory
  • Know how to use models and coding agents as leverage
  • Use evals, traces, failure analysis, and fast iteration to make AI systems dependable
  • Experienced backend, platform, or integration engineer who has shipped and operated production software
  • Can debug across SDKs, HTTP, OAuth, webhooks, queues, data stores, logs, and third-party APIs
  • Can turn an ambiguous failure into a minimal reproduction, a root cause, and a durable fix
  • Enjoy talking directly with technical users
  • Communicate clearly under uncertainty

Nice to have

  • TypeScript or Python in production
  • Experience building AI agents, copilots, workflow automation, or eval infrastructure
  • Experience with a developer platform, API product, support engineering, SRE, or incident response
  • Familiarity with OAuth 2.0, webhooks, rate limits, Postgres, queues, and cloud observability
  • Experience with support systems such as Plain, Zendesk, Intercom, or Salesforce
  • Public technical writing, open source contributions, or unusually good debugging notes

About the company

Composio is building infrastructure that allows AI agents to communicate with tools people use for work, including GitHub, Gmail, Notion, and Salesforce. They are a small team of engineers building the action layer for AI agents.