AI ENGINEER

Stellar IT Solutions LLC; Santa Clara (CA); On-site; USD 120,000 - 180,000; Full time

Job summary

Stellar IT Solutions LLC in Santa Clara, CA seeks an AI Engineer to design, develop, and deploy agentic AI systems that automate engineering workflows, with a focus on evaluation frameworks, telemetry pipelines, and observability standards.

You will ensure AI agents operate efficiently, reliably, and transparently, combining strong software engineering with AI observability, anomaly detection, and performance optimization to deliver scalable tooling.

Responsibilities

• Design, develop, and deploy AI agents that automate engineering workflows, including experiment configuration, results analysis, regression detection, and recommendations.
• Build and maintain evaluation harnesses for agentic systems (regression suites, golden sets, scoring rubrics) integrated into release pipelines.
• Architect ingestion and storage pipelines for agent telemetry at scale, ensuring fast and actionable queries during live incidents.

Job description

Job Description: AI Engineer
Location: Santa Clara, CA (Onsite)
Duration: 6-12+ months (Contract)

Overview

We are seeking an innovative AI Engineer to design, develop, and deploy agentic AI systems that automate engineering workflows. This role will focus on building evaluation frameworks, telemetry pipelines, and observability standards to ensure AI agents operate efficiently, reliably, and transparently. The ideal candidate will combine strong engineering skills with expertise in AI observability, anomaly detection, and performance optimization.

Key Responsibilities

• Design, develop, and deploy AI agents that automate engineering workflows, including experiment configuration, results analysis, regression detection, and recommendations.
• Build and maintain evaluation harnesses for agentic systems (regression suites, golden sets, scoring rubrics) integrated into release pipelines.
• Architect ingestion and storage pipelines for agent telemetry at scale, ensuring fast and actionable queries during live incidents.
• Instrument cost, latency, and token consumption per agent, tool, and routing path, surfacing efficiency signals for platform decisions.