About the role

We are looking for an Agentic AI Engineer to design and build AI agents that continuously analyze ServiceNow Discovery logs, classify failures, perform root cause analysis, and recommend or generate corrective actions at enterprise scale across millions of infrastructure targets. You will develop agentic observability capabilities for MID Servers and Discovery schedules, integrate LLM APIs including OpenAI and Anthropic using RAG and vector databases, and convert operational runbooks into reusable agentic workflows using advanced Python engineering. Strong infrastructure troubleshooting and network protocol knowledge is required alongside production-grade Python and CI/CD experience.

What you will do

  • Design and build AI agents that continuously analyze Discovery logs, execution results, errors, and failed discoveries at scale.
  • Develop agents capable of classifying and correlating failures, performing troubleshooting, identifying probable root causes, and recommending corrective actions.
  • Build capabilities for agents to analyze and recommend or generate corrections to ServiceNow Discovery probes and patterns, with appropriate testing, guardrails, and human approval before production changes.
  • Convert operational knowledge, runbooks, and recurring troubleshooting procedures into reusable agentic workflows, progressively reducing manual investigation and improving Discovery reliability.
  • Design and build AI agents that continuously assess the health of the ServiceNow Discovery ecosystem, including MID Servers, discovery schedules/playbooks, target execution, throughput, latency, failures, retries, and discovery coverage.
  • Develop agents that regularly collect, aggregate, and interpret metrics and telemetry from ServiceNow Discovery, MID Servers, logs, monitoring platforms, and other relevant data sources.

Must haves

  • Advanced Python development experience of at least 4+ years, and REST API design capabilities with experience building APIs, data-processing pipelines, integrations, automation, and production-grade engineering solutions.
  • Strong experience with modern software development and SDLC practices and toolchains, including Git/GitHub, Jenkins or equivalent CI/CD platforms, artifact repositories, automated testing, code quality/security scanning, release management, and deployment automation.
  • Practical experience integrating Gen AI APIs into software applications, e.g. OpenAI, Anthropic, and a working understanding of developer-level concepts like Retrieval-Augmented Generation (RAG) and Vector databases. (Note: We need software builders, not Machine Learning researchers.)
  • Practical knowledge of Infrastructure Engineering with Linux, Windows Server, compute, virtualization/cloud infrastructure, authentication, processes/services, and infrastructure troubleshooting.
  • Working knowledge of TCP/IP, DNS, routing, firewalls, ports, SSH, WMI/WinRM, SNMP, HTTP/S, and common network and infrastructure troubleshooting techniques.
  • Experience with high-volume logs, metrics, errors, and operational datasets to identify patterns, anomalies, trends, and root causes and turn them into actionable engineering improvements.
  • Upper-Intermediate English level.

Nice to haves

  • Hands-on experience with ServiceNow Discovery, including MID Servers, Discovery Patterns/Probes, credentials, schedules, Discovery Status, ECC Queue, and troubleshooting Discovery failures.
  • Experience developing or modifying ServiceNow Discovery Patterns and Probes and understanding how infrastructure attributes and relationships are discovered.
  • Experience with ServiceNow CMDB/CSDM, Configuration Items (CIs), identification/reconciliation, relationships, and CMDB data quality.
  • Experience with observability technologies such as Prometheus, OpenTelemetry, alongside Grafana.

Perks

  • Growth without limits: build your skills through mentorship, internal TechTalks, challenging projects, and a dedicated annual learning budget
  • Competitive compensation: get recognition that reflects your skills and impact, with regular performance and compensation reviews
  • Flexibility: work 100% remotely with flexible hours that support focus, autonomy, and a healthy work rhythm
  • Meaningful, modern projects: build impactful products using modern technologies alongside global teams and leading brands
  • Collaborative culture: join a supportive environment with zero micromanagement where ideas are welcomed and contributions are recognized
  • Well-being & support: access local well-being programs and people-focused support tailored to your location

Didn’t find the perfect fit?

Subscribe to get notified about new roles that match your skills and interests.

Get role alerts

Hiring process timeline

We designed our hiring process to be fast, transparent, and convenient — so you always know what to expect and can move through the steps without unnecessary delays.

lightning-iconA quick note

After applying, keep an eye on your inbox — including your spam folder. Occasionally, emails from our hiring platform, LaunchPod, may land there.

1

Tell us about yourself

Submit a short application form.

2

Pass a quick test

Pass a 30’- 60’ test.

3

Record a short video

Introduce yourself on video to fast-track your application process.

4

Meet our team

Once you pass the video review, grab a spot on our calendar for a technical interview.

5

Get an offer

Welcome to AgileEngine!

FAQ

Have any questions?

What is the work format and schedule?

We are a remote-first company, so all our positions are remote. Schedules are flexible, but the main requirement is to have an overlap with your client’s schedule to ensure smooth collaboration. Specific details depend on the project and are discussed during the interview process.

What level of English is required?

We look for Upper-Intermediate (B2) proficiency or higher. Since you will be collaborating with international teams and global clients (including Fortune 500 companies), English is a part of your daily work.

Does AgileEngine provide work equipment?

It depends on your location. We provide equipment in Ukraine, Poland, Argentina, Colombia, Mexico, Brazil, Guatemala, Portugal, Spain, and India. In the USA, equipment is usually provided by the client; otherwise, you will be expected to use your own setup.

What opportunities for professional growth do you offer?

We support continuous growth through personalized development paths tailored to each expert. Also, you can expect:

  • An annual learning and development budget
  • Internal workshops, tech talks, and mentorship programs
  • Opportunities to switch projects or grow into new roles over time

What does a typical team look like, and what tools do you use?

Teams vary by project, but you’ll usually work with a mix of experts across different fields, along with a delivery or project manager who supports collaboration and onboarding.

For day-to-day work, teams commonly use tools like Jira and Google Workspace, along with communication platforms such as Google Chat. Depending on the client, you may also work with Slack, Confluence, Notion, or similar tools.

Need help?

Want more details? See full FAQ

If something doesn’t work or you have questions regarding your application process, drop us a line.

    Scroll to Top