Senior AI Engineer ID80138
On-siteTernopil, Ternopil, Ukraine
Job Summary
Design and build AI agents that continuously analyze ServiceNow Discovery logs, classify failures, and perform root cause analysis at enterprise scale. Develop agentic observability capabilities for MID Servers and Discovery schedules, integrating LLM APIs with RAG and vector databases to convert operational runbooks into reusable workflows. Assess the health of the Discovery ecosystem, including target execution, latency, and coverage, while regularly collecting and interpreting metrics from monitoring platforms. Apply advanced Python engineering and infrastructure troubleshooting skills to reduce manual investigation and improve Discovery reliability. Work 100% remotely with flexible hours within an Inc. 5000 company recognized as a Best Place to Work.
Required Qualifications
- Advanced Python development experience of at least 4+ years
- REST API design capabilities
- Experience building APIs
- Data-processing pipelines
- Integrations
- Automation
- Production-grade engineering solutions
- Strong experience with modern software development and SDLC practices
- Git/GitHub
- Jenkins or equivalent CI/CD platforms
- Artifact repositories
- Automated testing
- Code quality/security scanning
- Release management
- Deployment automation
- Practical experience integrating Gen AI APIs into software applications
- OpenAI
- Anthropic
- Retrieval-Augmented Generation (RAG)
- Vector databases
- Practical knowledge of Infrastructure Engineering
- Linux
- Windows Server
- Compute
- Virtualization/cloud infrastructure
- Authentication
- Processes/services
- Infrastructure troubleshooting
- TCP/IP
- DNS
- Routing
- Firewalls
- Ports
- SSH
- WMI/WinRM
- SNMP
- HTTP/S
- Common network and infrastructure troubleshooting techniques
- Experience with high-volume logs, metrics, errors, and operational datasets
- Upper-Intermediate English level
Desired Qualifications
- Hands-on experience with ServiceNow Discovery
- MID Servers
- Discovery Patterns/Probes
- Credentials
- Schedules
- Discovery Status
- ECC Queue
- Troubleshooting Discovery failures
- Experience developing or modifying ServiceNow Discovery Patterns and Probes
- Understanding how infrastructure attributes and relationships are discovered
- Experience with ServiceNow CMDB/CSDM
- Configuration Items (CIs)
- Identification/reconciliation
- Relationships
- CMDB data quality
- Experience with observability technologies such as Prometheus
- OpenTelemetry
- Grafana
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.