Remote Lead: Multi-Agent Systems Engineer

Zoho; United States; Remote; USD 120,000 - 170,000; Part time

Job summary

Agentic Workflow is seeking a skilled Multi-Agent Systems Engineer to design, develop, and stabilize autonomous multi-agent networks in a remote offshore setup. The role focuses on production-grade, stateful agents that collaborate, share context, call enterprise APIs, and handle failures gracefully to execute complex business operations independently.

The ideal candidate has 4–8 years in enterprise backend or distributed systems, expertise in Python/TypeScript, async programming, API design,

Qualifications

• 4–8 years of backend/web engineering or distributed systems experience
• 2+ years writing production-grade code for autonomous multi-agent environments
• Proficiency in Python or TypeScript and asynchronous programming
• Understanding of LLM cognitive limits, tool calling, and loop mitigation
• Certification: Professional ML Engineer or cloud ML credential (AWS/GCP/Azure)

Responsibilities

• Design multi-agent orchestration architectures using LangGraph, CrewAI, AutoGen or Semantic Kernel
• Build stateful deterministic and non-deterministic state machines and agent communications
• Implement secure tool execution frameworks to call REST APIs, query SQL and process files
• Configure memory layers: short-term memory and long-term semantic storage
• Establish HITL validation checkpoints for sensitive operations
• Enhance reasoning and planning with ReAct, Plan-and-Solve, self-reflection loops
• Implement observability and tracing with LangSmith, Arize Phoenix or Datadog

Skills

Python

TypeScript

Asyncio

State management

API design

Relational databases

Education

Professional ML Engineer or Specialty ML credential (AWS/GCP/Azure)

Tools

LangGraph

CrewAI

AutoGen

Semantic Kernel

LangSmith

Arize Phoenix

Datadog LLM Observability

Job description

Agentic Workflow is seeking a skilled Multi-Agent Systems Engineer to design, develop, and stabilize autonomous multi-agent networks in a remote offshore setup. The role focuses on production-grade, stateful agents that collaborate, share context, call enterprise APIs, and handle failures gracefully to execute complex business operations independently.

The ideal candidate has 4–8 years in enterprise backend or distributed systems, expertise in Python/TypeScript, async programming, API design,