Senior Software Engineer - AI Agents

UMATR; San Francisco (CA); On-site; USD 150,000 - 190,000; Full time

Job summary

UMATR is seeking a Senior Software Engineer – AI Agents to design, build and deploy production AI agents across full-stack architecture from agent orchestration to cloud infrastructure. You will work with TypeScript, Node.js, NestJS and React, deploying on AWS and owning the production lifecycle.

The role requires strong system design skills, hands-on LLM experience, and a track record of shipping AI agents to real users.

Qualifications

• 5-7 years of software engineering experience.
• Strong production experience with Node.js, TypeScript, NestJS and React.
• Proven experience building and deploying at least one AI agent into production, beyond proof-of-concept or prototype stage.
• Experience deploying and maintaining applications on AWS serving real users or production traffic.
• Hands-on experience with LLM and agent frameworks such as LangChain or LlamaIndex.
• Experience designing evals, feedback loops or reliability systems for AI applications.
• Production experience with observability tooling such as Datadog, OpenTelemetry or CloudWatch.
• Experience managing production incidents from detection through investigation and resolution.
• Strong system design skills and the ability to explain architectural decisions and technical trade-offs.
• Comfortable owning projects across the full stack rather than working exclusively within the AI layer.

Responsibilities

• Design, build and deploy production AI agents that automate complex operational workflows.
• Build full-stack features using TypeScript, Node.js, NestJS and React.
• Develop agent infrastructure, orchestration and supporting backend services.
• Build evaluation frameworks and feedback loops to measure and continuously improve agent performance.
• Work with large-scale operational, order and product data.
• Deploy and operate applications across AWS, including Lambda, ECS, RDS and S3.
• Manage infrastructure using Terraform.
• Build observability into systems from day one through logging, tracing, monitoring and alerting.
• Own systems throughout their production lifecycle, including debugging and incident resolution.
• Make and own architectural decisions across the wider platform.

Skills

Node.js

TypeScript

NestJS

React

AWS

LangChain

LlamaIndex

LLM

Observability

Terraform

Tools

Terraform

Datadog

OpenTelemetry

CloudWatch

Job description

We’re partnering with a high-growth AI company building autonomous agents that don’t just assist with work - they actually do it.

Their agents are already taking ownership of complex, business-critical workflows across the supply chain, making decisions across orders, inventory, customers and suppliers in real time.

They’re now looking for a Senior Software Engineer – AI Agents to build the next generation of these systems.

You’ll work across the full stack, from the agent architecture, orchestration and evaluation layer through to backend services, user-facing products and cloud infrastructure. This is a chance to build production AI systems from the ground up, ship them to real customers and own what happens once they’re live.

What You’ll Do:

• Design, build and deploy production AI agents that automate complex operational workflows.
• Build full-stack features using TypeScript, Node.js, NestJS and React.
• Develop agent infrastructure, orchestration and supporting backend services.
• Build evaluation frameworks and feedback loops to measure and continuously improve agent performance.
• Work with large-scale operational, order and product data.
• Deploy and operate applications across AWS, including Lambda, ECS, RDS and S3.
• Manage infrastructure using Terraform.
• Build observability into systems from day one through logging, tracing, monitoring and alerting.
• Own systems throughout their production lifecycle, including debugging and incident resolution.
• Make and own architectural decisions across the wider platform.

What We’re Looking For:

• 5-7 years of software engineering experience.
• Strong production experience with Node.js, TypeScript, NestJS and React.
• Proven experience building and deploying at least one AI agent into production, beyond proof-of-concept or prototype stage.
• Experience deploying and maintaining applications on AWS serving real users or production traffic.
• Hands-on experience with LLM and agent frameworks such as LangChain or LlamaIndex.
• Experience designing evals, feedback loops or reliability systems for AI applications.
• Production experience with observability tooling such as Datadog, OpenTelemetry or CloudWatch.
• Experience managing production incidents from detection through investigation and resolution.
• Strong system design skills and the ability to explain architectural decisions and technical trade-offs.
• Comfortable owning projects across the full stack rather than working exclusively within the AI layer.