Agentic Workflow Lead

Loom; United States; Remote; USD 150,000 - 230,000; Full time

Benefits offered by this job

Equity participation

Remote work support across US

Job summary

Loom seeks a senior engineer to lead production-grade, agentic AI solutions for enterprise customers from scoping to deployment. You will architect runtimes, integrate with client codebases, and own operational success across multiple engagements.

You will mentor practitioners, optimize cost, latency, and safety, and drive architectural decisions while delivering value in real-world environments.

Qualifications

• Senior-level experience building and operating multi-agent systems in production.
• Experience with an agent framework such as LangGraph, CrewAI, AutoGen, or equivalent.
• Direct experience running LLM applications at scale.
• Practical knowledge of evaluation, safety guardrails, cost management, and latency optimization.
• Comfort delivering software within a customer\'s existing codebase and infrastructure.

Responsibilities

• Direct multi-agent system engagements from discovery and design through production.
• Architect agent runtimes, tool integrations, and evaluation pipelines.
• Work inside customer codebases and infrastructure to deliver practical solutions under real constraints.
• Establish repeatable patterns for agent design, evaluation, safety controls, and production readiness.
• Monitor and improve the operation of LLM systems, including cost, latency, quality, and guardrails.
• Advise on architectural decisions and mentor other practitioners.

Skills

Multi-agent systems

Agent frameworks

LLM applications

Tools

LangGraph

CrewAI

AutoGen

Job description

Role overviewLead the delivery of production-grade agentic AI solutions for enterprise customers, from initial scoping through deployment. The work combines hands-on architecture, customer-embedded engineering, operational ownership, and technical leadership across concurrent engagements.

Responsibilities

• Direct multi-agent system engagements from discovery and design through production.
• Architect agent runtimes, tool integrations, and evaluation pipelines.
• Work inside customer codebases and infrastructure to deliver practical solutions under real constraints.
• Establish repeatable patterns for agent design, evaluation, safety controls, and production readiness.
• Monitor and improve the operation of LLM systems, including cost, latency, quality, and guardrails.
• Advise on architectural decisions and mentor other practitioners.

Requirements

• Senior-level experience building and operating multi-agent systems in production.
• A proven track record with an agent framework such as LangGraph, CrewAI, AutoGen, or an equivalent system.
• Direct experience running LLM applications at scale.
• Practical knowledge of evaluation, safety guardrails, cost management, and latency optimization.
• Comfort delivering software within a customer's existing codebase and infrastructure.
• Strong technical communication, with the ability to explain trade-offs to engineers and executives.

Nice to have

• Experience in a forward-deployed engineering environment.
• Background in distributed systems or inference infrastructure.
• Open-source contributions to agent frameworks or evaluation tooling.

Benefits and work setup

• Remote work is supported across the United States, Canada, Mexico, and India.
• The role offers direct ownership of engagement outcomes, close collaboration with senior technical leaders, and transparent, level-based compensation with equity participation.