ML Evaluation Engineer: Metrics, Thresholds & Autonomy

Nuvnext; Región Centro; Hybrid; MXN 420,000 - 660,000; Full time

Job summary

Nuvnext in Guadalajara is seeking an in-person Full-time Engineer to design and run evaluation systems for agent-based products. You’ll collaborate with founders, build real-case evaluation sets, and measure hits, errors, cost, and time to improve models before deployment.

You’ll use Python for analysis, and you’ll explain results clearly to non-technical stakeholders while pushing for rigorous experimental methodology.

Qualifications

• Fluency in statistics and experimental method.
• Ability to explain results to non-technical audiences.
• Proficient in Python for analysis and automation.

Responsibilities

• Build evaluation sets from real operational cases.
• Measure hits, errors, cost and time for agents.
• Compare models and configurations with method, not impressions.
• Define thresholds that allow moving up a level of autonomy.

Skills

Statistics

Experimental method

Communication of results

Tools

Python

Job description

Nuvnext in Guadalajara is seeking an in-person Full-time Engineer to design and run evaluation systems for agent-based products. You’ll collaborate with founders, build real-case evaluation sets, and measure hits, errors, cost, and time to improve models before deployment.

You’ll use Python for analysis, and you’ll explain results clearly to non-technical stakeholders while pushing for rigorous experimental methodology.