About this role
This role involves performing human-in-the-loop testing and evaluation of agentic storage management experiences. You will support the calibration and validation of AI-powered storage agents by providing expert manual evaluation of user journeys that complement existing LLM-based evaluation pipelines. As a Storage Management Evaluation Specialist, your expertise in storage administration will be essential for assessing the completeness, accuracy, and practical value of agent-generated recommendations from an industry practitioner''s perspective.
Key Responsibilities- Discovery Evaluation: Test User Journeys across migration options to calibrate agent response completeness and accuracy of presented options.
- Planning Evaluation: Assess agent guidance on trade-offs between Online and Offline transfer methods, including Cloud Interconnect ROI analysis and time estimates across varying file sizes and object counts.
- Validation Evaluation: Execute simulation and dry-run migration User Journeys; identify issues that could cause migration failures.
- Execution Evaluation: Initiate actual transfer operations via agent interfaces and assess operational reliability.
- Reporting Evaluation: Evaluate agent-generated progress tracking, outcome reporting, and variance analysis against migration plans.
- Traffic Simulation: Simulate realistic storage traffic in test projects to create representative evaluation conditions.
- Agent Invocation & Feedback: Invoke AI Agents with natural language queries and provide subjective, expert-level feedback on outcomes.
- Scoring Calibration: Calibrate offline scoring mechanisms using evaluation findings to improve automated assessment accuracy.
- 3P Agent Testing: Test third-party agent blueprints built for customers on the Cloud Storage MCP platform.
- Completed User Journey evaluation reports for each agent (per 10-week cycle).
- Documented subjective insights and actionable feedback on agent responses from a storage admin persona.
- Calibration data and recommendations for the offline scoring mechanism.
- Issue logs identifying agent failure modes, inaccuracies, or gaps.
- Summary reports comparing agent-planned outcomes vs. actual migration results.
- Storage administration experience with a strong understanding of cloud storage concepts, data migration strategies, and enterprise storage management practices.
- Familiarity with cloud storage platforms (AWS S3, GCS, Azure).
- Hands-on experience with data migration — including online/offline transfer methods, Cloud Interconnect, and transfer sizing considerations.
- Ability to evaluate AI/LLM-generated recommendations from a practitioner''s perspective, identifying gaps in completeness and accuracy.
- Strong written communication skills for documenting evaluation findings and providing structured feedback.
- Comfortable working with natural language interfaces and conversational AI tools.
- Background in storage performance analysis, security auditing, or storage intelligence/analytics.
- Prior experience in QA, evaluation, or red-teaming of AI/ML systems.
- Familiarity with MCP (Model Context Protocol) or agentic AI frameworks.
This is a W-2 employment position with flexible hours, allowing for remote work within the US.
CompensationThe hourly compensation for this role ranges from $45 to $60.
EligibilityApplicants must be authorized to work in the United States.