Jobs on TAL
All jobsOnsiteQuality Assuranceai/ml infra1-3 yearsms excel
OnsiteMid Levelai/ml infra

AI Benchmarking Lead, Performance Benchmarking Evaluation

AmazonHyderabad, Telangana, IndiaPosted 16 May 2026

Amazon is seeking an AI Benchmarking Lead to support their Seller Assistant Gen-AI copilot by ensuring evaluation reliability and accuracy. The role involves auditing model performance, calibrating quality standards, and driving SOP improvements across international markets. Candidates will use SQL and Python to analyze data and improve evaluation metrics. This position reports within the ML data operations team at a massive scale.

Matched by TAL

50k new jobs listed every day. Install TAL to find more jobs like this.

Install TAL

Experience

1-3 years

Function

Quality Assurance

Work mode

Onsite, India

Company

Tier 1

What you will work on

Amazon is seeking an AI Benchmarking Lead to support their Seller Assistant Gen-AI copilot by ensuring evaluation reliability and accuracy. The role involves auditing model performance, calibrating quality standards, and driving SOP improvements across international markets. Candidates will use SQL and Python to analyze data and improve evaluation metrics. This position reports within the ML data operations team at a massive scale.

TAL's take

Quality 75/1005/5 clarityTier 1 company

High-impact AI benchmarking role at Amazon working on large-scale Gen-AI products with clear performance metrics.

The JD provides a very clear breakdown of benchmarking responsibilities, team scale, and specific toolsets required for the AI quality role.

Salaries at Amazon

25.8 LPA average

Based on 3,341 Grapevine salary entries for Amazon.

View all salaries

Information Technology

0 - 2 years | L3

7 LPA average

Range: 2 - 12 LPA

Other

0 - 2 years | L3

3 LPA average

Range: 2 - 4 LPA

Human Resources

0 - 2 years | L3

6 LPA average

Range: 5 - 7 LPA

Accounting

0 - 2 years | L3

2 LPA average

Range: 2 - 2 LPA

Must haves

  • Bachelor's degree or equivalent
  • Experience in natural language data labeling or annotation
  • Proficiency in MS Excel
  • Basic understanding of SQL and Python
  • Strong verbal and written communication skills in English

Tools and skills

ms excelsqlpythonmicrosoft office

Nice to have: sql, python.

About the company

Global FAANG company with a strong engineering presence in India.

Posts mentioning Amazon