M

AI Agent Engineer

Manifest Global
NewPosted today

LOCATION

New Delhi · Onsite

EXPERIENCE

Not specified

SKILLS REQUIRED

Agent orchestrationLarge Language ModelsPythonModel EvaluationTool CallingRAGHuman in the Loop

Job description

Overview

Build production AI agents across Manifest Global's portfolio brands (Cialfo, BridgeU, Kaaiser, Explore) that reason, plan, and take action across tools to complete real counseling, admissions outreach, and operational workflows.

What you'll do

  • Design and build production AI agents across Manifest's brands, starting with the highest-leverage workflows in counseling, admissions outreach, and operational triage.
  • Own architecture decisions: model selection, tool use, memory, evaluation, guardrails, and the orchestration layer.
  • Build the abstractions that turn one good agent into a platform.
  • 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.
  • Build the safety layer: when an agent should stop, escalate, or ask.
  • Work directly with product and engineering teams across Cialfo, BridgeU, Kaaiser, and Explore to ship agents into existing user surfaces.
  • Translate fuzzy user problems into agent specifications that can be built.
  • Close the loop between user feedback and model behaviour.
  • Set the standard for how AI agents are built at Manifest, including tooling, frameworks, model providers, evaluation harness, and deployment patterns.
  • Stay close to the research frontier and ship accordingly.

What you'll need

  • Experience building software that runs in production.
  • Experience shipping something agentic that users use, not only a prototype.
  • Working knowledge of current LLM and agent frontier, including model providers, orchestration patterns, and agent framework limitations.
  • Ability to evaluate systems without a single correct answer.
  • Production-quality Python.
  • Comfort with the surrounding stack: vector stores, prompt management, evaluation frameworks, observability tooling.
  • Systems thinking: mapping reasoning, state, tool calls, and human-in-the-loop points in a workflow.
  • Self-directed decision-making in an environment without a finished playbook.

Details

  • Location: New Delhi.

Read the full description and apply on the company’s own careers page.

Stay safe

Hiring on Abekus is free for applicants

We never charge a fee, and employers are prohibited from doing so. If a recruiter asks for payment, please report them right away.

AI Agent Engineer