You and the process

With a person
Anna, in-house recruiter
9 years hiring engineers
30 minutes with a real recruiter
They read your CV with you, on a call, and say where the offers are being lost.
Didn’t find what you were looking for? Tell us what to build
Netskope

AI Engineer

  • Remote
  • 3-6 years

Salary

Not stated

Similar roles pay $125K - 210K a year · our estimate

AI summary

For members

The whole posting in a few lines. Sign up to read it here and on every role you open.

Sign Up to Read

Description

Taking AI agents from a demo to production takes real software engineering discipline. The company is hiring an AI Agent Engineer to build agentic systems that scale, stay secure, and can be fully audited.

The job is not about endlessly adjusting prompts until the output looks right. You will design spec-driven architectures made of an orchestrator and sub-agents, classify sensitive data, connect tool gateways, and write thorough test cases. You will work with Product, Security, and Cloud Architecture so that each agent stays within its guardrails and risk tier.

Responsibilities

  • Write complete agent specifications covering purpose, capabilities, input and output contracts, guardrails, and tool boundaries, at the rigor of a safety-critical system rather than a brief README.
  • Build orchestrator agents that delegate to specialized sub-agents, keeping the orchestrator limited to coordination and never letting it do the work itself.
  • Write and test system prompts, and design tool schemas that remain accurate when an agent picks from fifteen or twenty tools rather than three.
  • Work with the Data Steward to classify the sensitivity of each agent's data, and with the Product Owner and Architect to set its risk tier before registration.
  • For every agent capability, decide whether deterministic logic or model judgment fits better, and write tests that confirm it meets that standard.
  • Build each agent on the platform's tool gateway so that it can only touch what it is registered and approved to use.
  • Design for scale from the start: isolated sessions, predictable failure behavior, and no reliance on conditions that only hold in a single test run.
  • Assemble the evidence a reviewer needs before approving an agent for production, including test results, guardrail coverage, and behavioral results, presented clearly enough for someone else to follow the reasoning.

Requirements

  • At least 4 years of experience building production software, including 1-2 years building LLM-powered agents that make their own tool-use decisions. Chatbots and RAG pipelines do not count.
  • Hands-on experience with at least one agent orchestration framework such as LangGraph, Bedrock AgentCore, CrewAI, AutoGen, or similar, and the ability to explain why you would choose one over another for a given problem.
  • Working knowledge of the Model Context Protocol, including building or integrating MCP servers and clients and knowing where tool selection tends to fail.
  • A disciplined prompt engineering practice: versioning changes and testing them against a set of cases before release, rather than iterating in a playground.
  • Ability to write precise specifications covering boundaries, failure modes, and test criteria. The team documents everything and peer-reviews all of it, so this is required.
  • Enough AWS knowledge (Lambda, IAM roles, Bedrock) to understand how your agents run. Infrastructure itself is owned by the Cloud Engineers.
  • Strong advantage: experience designing systems where one agent performs a task and a separate agent checks it, with separation of duties built into the architecture rather than documented afterward.
  • Strong advantage: any exposure to red-teaming or adversarial testing of AI systems, even if it was not your main role.
  • Strong advantage: time in a regulated environment (SOX, SOC2, GDPR, ISO27001), where working correctly was never the only standard.
  • Strong advantage: some familiarity with agent memory, both short-term session memory and more durable storage, and what each choice costs in auditability.

About the company

Netskope

  • Industry: Cybersecurity

Also hiring in United States, Spain and United Kingdom

10 of their 19 open roles are remote

Your chances

Worth a look before you spend an evening tailoring a CV for it.

  • 19 checks run
  • 1 red flag

Still hiring?

13 checks

No red flags

How crowded?

6 checks

1 red flag

Fits Me

How well does this role fit you?

Answer a few questions or drop your CV, and every role gets a fit score with the reasons, this one first.

  • Your field
  • Level
  • Stack
  • Work model
  • Salary floor
  • Must-haves
Details9 facts · Role, Location, Compensation, Company
Tech stack
  • AWS
  • LLMs
  • RAG
  • LangChain
Industry
Cybersecurity
Specialty
ML
Region
United States
Pay period
Annual
Show 4 more factsShow less

Role

Category
Data & Analytics
Specialty
ML
Experience
4+ years
Tech stack
  • AWS
  • LLMs
  • RAG
  • LangChain

Location

Work model
Remote
Region
United States

Compensation

Salary
Salary by agreement
Pay period
Annual

Company

Industry
Cybersecurity

Something wrong with this vacancy?

Similar vacancies

Share this vacancy

What's wrong with it?

The employer never sees who reported.

Reason