GenAI Engineer: RAG Pipelines & Network Troubleshooting Copilot

Valiant Technologies LLC; Palo Alto (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

VALIANT TECHNOLOGIES LLC is seeking an AI/ML engineer to build GenAI-powered tools for network troubleshooting. You will design RAG pipelines, grounding with citations, and deploy reliable services with CI/CD, testing, and monitoring.

You will work with data engineering and platform teams to translate network issues into KPIs, RCA steps, and actionable remediation plans, while focusing on latency, accuracy, and cost controls.

Qualifications

• 3–5 years of experience in AI/ML engineering, data engineering, or applied data science delivering production-grade solutions.
• Strong Python and SQL skills; mastery working with large-scale telemetry/time-series datasets and building reliable, testable data transformations.
• Experience grounding outputs with traceable evidence and citations is a plus.
• Familiarity with GenAI frameworks and tooling including Azure services.

Responsibilities

• Build, deploy, and operate GenAI-powered tools that accelerate network troubleshooting with citations.
• Design and implement RAG pipelines including embeddings, vector search, grounding, and citations.
• Ship reliable services with CI/CD, automated tests, canary releases, monitoring, and SLOs.
• Implement evaluation and continuous monitoring with offline/online eval harnesses and drift detection.
• Integrate with internal systems and tools including alarms, KPI platforms, tickets, and dashboards.
• Collaborate cross-functionally to translate network issues into measurable KPIs and actionable outputs.

Skills

Python

SQL

Azure Functions

Azure DevOps

Git

OpenTelemetry

GenAI frameworks

prompt design

ML/Ops

data engineering

Education

BS/MS in CS/EE/Data Science

Tools

Semantic Kernel

LangChain/LlamaIndex

MLflow/Model Registry

vector databases

Job description

VALIANT TECHNOLOGIES LLC is seeking an AI/ML engineer to build GenAI-powered tools for network troubleshooting. You will design RAG pipelines, grounding with citations, and deploy reliable services with CI/CD, testing, and monitoring.

You will work with data engineering and platform teams to translate network issues into KPIs, RCA steps, and actionable remediation plans, while focusing on latency, accuracy, and cost controls.