
AI Benchmark Engineer | Native Language Specialist - Indonesian - Remote
About this role
Lilt-production offers a remote, freelance AI Benchmark Engineer position focusing on the Indonesian language to design and validate evaluation tasks for large language models. This role suits experienced software engineers with native fluency in Indonesian who want flexible, project-based supplemental work.
Role Overview
Lilt-production seeks a native-speaking software engineer to build and verify Terminal-Bench tasks testing large language models on multilingual software challenges. The contractor works remotely on a freelance basis to evaluate coding agents, build native-language task environments, and analyze model limitations in non-English data processing.
Key Responsibilities
Requirements
Skills and Tools
About the Company
Lilt-production builds rigorous evaluation suites to test large language models on multilingual software challenges and measures robustness across prompt language effects. The organization connects a global community of linguists, subject matter experts, and language professionals to advance language technology.
How to Apply
Interested candidates should submit 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 contractor opportunity that is best suited as a supplemental income stream rather than a primary job.
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 language proficiency is required?
Candidates must have native or near-native fluency in Indonesian with a deep understanding of its grammar and phrasing rules, alongside high English proficiency.
What technical experience is necessary?
Applicants need at least five years of software engineering industry experience, strong proficiency in Python and shell scripting, and familiarity with Terminal-based development workflows.
How does the application process work?
Candidates submit an application with an English CV, complete a GenAI assessment, and finalize onboarding in the system.
The application is on the official lilt-production careers page.
Apply on company site