Member Technical Staff - Applied AI Engineer (US Timing)
Composio (company site, opens in a new tab)2–4 yrsBengaluruOn-siteDirect career pageEst. 15–28 LPA
Posted on 7 Sept
Reach people at Composio
People at this company you can reach
Log in to see who works here
Create a free account or log in to see the people at Composio you could write to:
- Recruiters & HR
- People in this function
- Work addresses
Your match
Against your primary resume
Log in to see your match score
Create a free account or log in to unlock your CV match score across:
- Role fit
- Experience
- Industry relevance
Protocol Intelligence
How competitive this role is
Competition
Background fit
Strictness
Log in to see why each signal reads the way it does.
Job description
Structured overview of role & requirements
About This Role
- Build and deploy agentic AI workflows to automate customer support tasks including classification, diagnosis, response drafting, and follow-up.
- Design and maintain safe, human-in-the-loop AI systems with guardrails, evaluation suites, and escalation paths to ensure trustworthy support automation.
- Collaborate directly with customers and internal teams to identify systemic issues and shift support tasks into reliable production software workflows.
Minimum Requirements
- 2–4 years of professional software engineering experience.
- Experience building production AI systems with language models, multi-step workflows, and agent memory.
- Strong backend/platform/backend integration engineering skills including debugging SDKs, APIs, OAuth, webhooks, queues, and data stores.
- Work location: Bengaluru; work hours aligned with US timings.
Ideal Candidate Profile
- Experienced applied AI engineer who can leverage language models and coding agents for reliable, high-leverage automation with a focus on trust and failure analysis.
- Comfortable working closely with customers to translate vague support problems into technical workflows and software solutions with measurable outcomes.
- Skilled at modeling workflows for support functions with clear states, permissions, handoffs, and escalation, focusing on automating root causes rather than symptoms.