AI Agent Engineer
Cialfo
| Company | Cialfo |
| Category | Engineering |
| Location | Delhi |
| Remote | On-site (inferred) |
| Employment | Not stated |
| Level | Not stated |
| Salary | Not stated by the employer |
| Posted | 31 May 2026 |
| Last verified | 30 Jul 2026 |
| Source | Employer career page (greenhouse) |
Description
About Manifest Global
Manifest Global is building the infrastructure for global human capital mobility - connecting students, schools, universities, and employers across 50+ countries. Our portfolio spans Cialfo (AI-powered college counseling, 2,000+ schools), BridgeU (university guidance for international schools globally), Kaaiser (trusted study abroad counseling across India and Southeast Asia), and Explore (AI-powered university outreach, 1,000+ university partners). Together, we move talent across borders at scale. $80M raised. Still early.
What This Role Is
AI agents — systems that reason, plan, take action across tools, and complete real work end-to-end — have moved from research demos to production infrastructure in the last eighteen months. The companies that build them well will define the next decade of what software is and what people do.
Manifest Global sits at one of the most operationally complex intersections in the world. Every day, our platforms move students between continents, counselors between conversations, applications between deadlines, universities between recruiting cycles, and agents between thousands of families making generational decisions. The work is high-stakes, high-volume, and full of judgment calls — exactly the kind of work that breaks under brittle automation and exactly the kind of work AI agents, built properly, can transform.
That is the bet behind this role. Not chatbots. Not wrappers. Agents that actually do the work — drafting university shortlists with reasoning a counselor would defend, surfacing the right student profile to the right admissions officer, catching the document that's about to make an application fail before a human sees it. Agents that hold context across long workflows. Agents that know when to escalate and when to keep going. Agents that get measurably better as more of the network uses them.
You will build those agents across the Manifest portfolio, in production, at a scale that matters.
What Makes This Role Different
Most companies hiring AI agent builders right now have one of two problems. They have the data but no real product surface to deploy into, so the agents sit in demos waiting for distribution. Or they have the distribution but the underlying data is too fragmented to support agents that work in production. Manifest has both. Cialfo's 2,000+ schools, BridgeU's international school footprint, Kaaiser's three decades of placement data, Explore's 1,000+ universities — that is the substrate. Saige, already live inside Cialfo, is proof that AI in this domain works when it is built well. Your job is to extend that surface across the portfolio.
This is not a research role. The agents you build will be used by real counselors, students, admissions officers, and partners within weeks of being shipped, not quarters. The feedback loop is tight. The accountability is direct. If an agent you built makes a bad shortlist, a counselor will tell you the same week. That is the speed at which good AI products get built right now, and it is the speed this role operates at.
The broader EdTech market is contracting. Manifest is growing. AI is the lever — and the people who build the agents will define what the next version of this company looks like.
What You Own
The agent platform
Design and build production AI agents across Manifest's brands, starting with the highest-leverage workflows in counseling, admissions outreach, and operational triage
Own the architecture decisions: model selection, tool use, memory, evaluation, guardrails, and the orchestration layer that holds it together
Build the abstractions that turn one good agent into a platform
Evaluation and reliability
Define what "working" means for each agent in measurable terms, and build the evaluation infrastructure that proves it
Own latency, cost, and accuracy as engineering disciplines, not afterthoughts
You found the opening. Now track it.Tracker, radar and AI drafts in one place.erioun.com →