Latest AI JobsBrowse Jobs
lilt-production logo

AI Benchmark Engineer | Native Language Specialist - Portuguese (Brazil) - Remote

lilt-productionBrazil (Remote)LiltLancer Community
Apply on company site
Salary
Not listed
Job type
Contract
Work mode
Remote
Experience
Mid · 1+ yrs
Posted
8 Sept 2026
Status
Open · checked 7d ago

About this role

Lilt-production is hiring a remote AI Benchmark Engineer and Native Language Specialist for Portuguese in Brazil to design, build, and validate evaluation tasks for large language models. This freelance contractor role suits experienced software engineers with native fluency in Portuguese who want a flexible supplemental income stream.

Role Overview

The AI Benchmark Engineer role focuses on testing the limits of large language models on multilingual software challenges. Working remotely from Brazil, the independent contractor builds realistic task environments using datasets and files in Portuguese. The position involves evaluating coding agents, identifying AI failure points, and executing calibration runs across different model tiers.

Key Responsibilities

Build realistic task environments using target-language datasets and files to measure multilingual handling.
Evaluate coding agents and identify prompt failures in Portuguese.
Write reliable verifier scripts and support reference implementation development.
Analyze execution logs and calibrate task difficulty from Easy to Very Hard against various model tiers.
Participate in a four-layer human quality control process alongside automated LLM-based checks.

Requirements

Minimum of 1 year of industry experience in software or prompt engineering.
Proven track record at leading technology companies or graduation from top-tier engineering universities.
Native or near-native fluency in Portuguese with high English proficiency.
Strong proficiency in Python, standard shell scripting, and data processing.
Extensive experience with Terminal or CLI-based development workflows and familiarity with coding agents.
Deep understanding of multilingual text processing pitfalls including Unicode normalization, encoding robustness, and locale-dependent conventions.

Skills and Tools

Python
Standard shell scripting
Terminal and CLI-based development workflows
Coding agents
AI model tiers including Haiku, Sonnet, and Opus

About the Company

Lilt-production builds rigorous evaluation suites to test large language models on multilingual software challenges. The organization seeks to measure multilingual robustness across prompt language effects, non-English data processing, and complex locale edge cases in terminal workflows.

How to Apply

To apply for this role, submit an application with an updated CV in English on the official company careers page.

Skills and tech stack

Questions candidates ask

Is this a full-time position?

No, this is a remote, freelance independent contractor opportunity intended as a supplemental income stream rather than a primary job.

What language proficiency is required?

Candidates must have native or near-native fluency in Portuguese with a deep understanding of its grammar and phrasing rules, alongside high English proficiency.

What are the time commitment expectations?

Most tasks require a minimum commitment of 2 hours per day or 15 to 20 hours per week.

What technical background do I need?

Applicants need at least 1 year of industry experience in software or prompt engineering, proficiency in Python and shell scripting, and familiarity with CLI-based workflows.

What is the application process?

The application process includes submitting an application with an English CV, completing a GenAI assessment, and finalizing system onboarding.

Ready to apply?

The application is on the official lilt-production careers page.

Apply on company site