Artificial Intelligence Engineer

About the Role

We are seeking a highly skilled AI Developer with strong Python expertise and practical experience developing Agentic AI applications using frameworks such as LangChain, LangGraph, CrewAI, and AutoGen. The ideal candidate will build, deploy, and package multi-agent LLM applications that interact with enterprise systems and external APIs.

Roles and Responsibilities

- Build LLM-based applications using LangChain, LangGraph, CrewAI, or AutoGen.

- Design intelligent agents, tools, memory systems, and RAG pipelines.

- Integrate LLMs with enterprise systems through REST APIs, connectors, and plugins.

- Use Docker to package and deploy AI agents as microservices.

- Implement prompt routing, context handling, and agent state management.

- Collaborate with DevOps teams to deploy applications in cloud/on-prem environments.

- Agent Development Design, build, test, and deploy all 16 GitHub Copilot Agent extensions across Splunk, Dynatrace, Midrange, MRD, and ServiceNow domains, following agent extension patterns defined by the Tech Lead.

- MCP Server Integrations Implement and maintain MCP server integrations for all target platforms Splunk (SHC, KVStore, Diag), Dynatrace (APIs, OneAgent), ServiceNow (CR/INC/SR), MRD (call flow, process workflow), and Active Directory.

- Prompt Engineering & Guardrails Write multi-turn prompt chains, structured tool definitions, and guardrail logic (intent classification, blast-radius limits, approval gates) for each agent; tune agent reasoning for domain-specific accuracy.

Must Have skills

1. MCP Protocol & REST API Integration Proficiency in implementing Model Context Protocol (MCP) servers; experience integrating agents with enterprise REST APIs (Splunk, Dynatrace, ServiceNow, Ansible).

2. Python (Advanced) + Testing Practices Advanced Python skills including async patterns, SDK usage, unit/integration testing (pytest), and secure coding practices for agent tool implementations.4. Python (6+) development skills.

- Experience with LangChain, LangGraph, CrewAI, AutoGen.

- LLM integration with OpenAI, Azure OpenAI, HuggingFace, etc.

- Retrieval-Augmented Generation (RAG) architecture and vector DBs.

- REST API integration and async programming in Python.

- Docker packaging and containerization of AI services.

- Git, JSON/YAML handling, Linux shell proficiency.