Professional Summary
Llm Evaluation Specialist with 6 years of experience in designing, executing, and analysing large-scale AI model evaluations. Combines deep knowledge of machine learning benchmarks with strong stakeholder communication to deliver actionable insights. Previously led evaluation frameworks at Accenture and currently mentors cross-functional teams on responsible AI practices.
Skills
- Communication
- Machine Learning Evaluation
- Experimental Design
- Data Analysis
- Stakeholder Collaboration
Experience
Llm Evaluation Specialist — Aceolution
- Architected a multi-stage evaluation pipeline that reduced model release cycle time by 40%.
- Collaborated with product and compliance teams to define responsible AI guardrails now used company-wide.
- Presented quarterly AI fairness and performance reports to executive leadership and external auditors.
- Mentored junior analysts on experimental design principles and statistical interpretation.
- Optimised cloud compute costs for evaluation workloads, saving $150K annually.
Technical Analyst — Accenture
- Designed and executed AB testing infrastructure for AI-driven customer segmentation models.
- Published findings on model drift and retraining cadence that shaped client AI governance frameworks.
- Coordinated cross-functional workshops to align engineering, legal, and marketing on AI experiment outcomes.
- Drove adoption of reproducible research practices by creating internal evaluation playbooks.
- Automated reporting dashboards that surfaced key performance metrics to client leadership weekly.
Education
M.S. Computer Science
Carnegie Mellon University
Certifications
- Certified Analytics Professional (CAP)
- TensorFlow Developer Certificate
Languages
English, Tamil