AI Agent Engineer

Kyndryl; Bengaluru; On-site; INR 350,000 - 600,000; Full time

Benefits offered by this job

Be Well programs

Hybrid-friendly culture

Personalized development goals

Continuous feedback

Cutting-edge learning opportunities

Coaching and hands-on experiences

Job summary

Kyndryl is seeking an Agent Engineer to design, build, and optimize reusable AI agents and workflows using Agent Builder and enterprise LLM toolkits. You will create specialized operational agents for ticket analysis, knowledge mining, SLA monitoring, CMDB assessments, and automated runbook generation across transition and BAU environments.

Responsibilities include translating requirements into multi-agent workflows, implementing tool calls, persistent memory, and human-in-the-loop paths,

Qualifications

• 5+ years in software, automation, or platform engineering.
• 2+ years hands-on GenAI/LLM/RAG/AI agent apps.
• Agent platform mastery with workflow design and deployment packaging.
• Proficiency in agentic patterns using LangChain, LangGraph, AutoGen, CrewAI.
• Strong knowledge of prompt engineering, function calls, JSON schema outputs, embeddings.
• Expertise in Python, REST APIs (FastAPI), Git, CI/CD, testing.
• Familiarity with AMS/ITSM domains, incidents, CMDB, SLAs.
• Ability to implement deterministic controls, audit logs, and TDLs.
• Proven end-to-end agent assets from design to release guides.

Responsibilities

• Translate AMS process requirements into single and multi-agent workflows.
• Build advanced agent capabilities including tool calling, memory, and human-in-the-loop escalation.

Skills

GenAI development

Agent frameworks

Python

REST APIs

CI/CD

ITSM knowledge

LLM prompt engineering

Vector search

Tools

Agent Builder

LangChain

LangGraph

AutoGen

CrewAI

LlamaIndex

Semantic Kernel

Job description

Role Overview

We are seeking an Agent Engineer to design, build, and optimize reusable AI agents and workflows using Agent Builder, modern agent frameworks, and enterprise LLM toolkits. In this role, you will create specialized operational agents for ticket analysis, knowledge mining, SLA tracking, CMDB assessments, and automated runbook generation across transition and BAU environments.

What You Will Do

• Agent Architecture & Workflow Design: Translate AMS process requirements into single and multi-agent workflows using Agent Builder, LangChain, LangGraph, AutoGen, or CrewAI.
• Tool & Memory Implementation: Build advanced agent capabilities including tool calling, function execution, persistent memory, reflection patterns, and human-in-the-loop escalation paths.

Why It Might Be a Fit

The career path ahead is full of exciting opportunities to grow and advance within the job family. With dedication and hard work, you can climb the ladder to higher bands, achieving coveted positions such as Principal Engineer or Vice President of Software.

Requirements

• 5+ years in software, automation, or platform engineering, with 2+ years dedicated to hands‑on development of GenAI, LLM, RAG, or AI agent applications (AMS/ITSM experience preferred).
• Agent Platform Mastery: Hands‑on experience with Agent Builder or enterprise agent development platforms, including workflow design, tool registration, multi‑agent orchestration, and deployment packaging.
• Agent Frameworks & Patterns: Proficiency in agentic patterns (planner, executor, critic, router, memory) using frameworks like LangChain, LangGraph, AutoGen, CrewAI, LlamaIndex, or Semantic Kernel.
• LLM & RAG Ecosystem: Strong knowledge of prompt/context engineering, function calling, JSON schema outputs, vector search, embeddings, re‑ranking, and model endpoints (OpenAI, Gemini, Claude, Llama).
• Core Software Engineering: Advanced Python skills, REST APIs (e.g., FastAPI), Git, CI/CD, unit testing, and building observable, fault‑tolerant distributed workflows.
• Enterprise ITSM Systems: Understanding of AMS/ITSM domains, including ServiceNow data structures (incidents, problems, CMDB, SLAs), ticket lifecycles, and runbook automation.
• Governance & Reliability: Ability to implement deterministic controls, human‑in‑the‑loop approvals, audit logs, and performance evaluation metrics to minimize hallucinations.
• Key Delivery Track Record: Proven experience producing end‑to‑end agent assets, from design specifications and prompt configurations to production test suites and release guides.

Benefits

• Be Well programs to support financial, mental, physical, and social health
• Dynamic, hybrid-friendly culture
• Personalized development goals aligned with ambitions
• Continuous feedback to keep inspired and on track
• Access to cutting‑edge learning opportunities
• Coaching and hands‑on experiences
• Empathy, restless learning, and devotion to shared success