AI Benchmark Engineer | Native Language Specialist - Arabic (Saudi Arabia)
New
L
LiltArtificial Intelligence
Saudi Arabia (remote)ContractSenior
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Languages
- Native or near-native Arabic proficiency; high English proficiency.
- Experience
- 5+ years of industry experience
- Required Skills
- PythonLLM
Requirements
- 5+ years of industry experience in software engineering.
- Native or near-native fluency in Arabic.
- High English proficiency.
- Strong proficiency in Python and standard shell scripting.
- Extensive experience with Terminal/CLI-based development workflows.
- Working familiarity with coding agents.
- Deep understanding of multilingual text processing including encoding, Unicode normalization, and locale conventions.
- Experience with bidirectional/RTL handling and typography.
- Ability to commit to 15-20 hours per week for project tasks.
Responsibilities
- Design, build, and validate Terminal-Bench tasks for LLM evaluation.
- Create high-signal assets using datasets and files in Arabic.
- Develop robust reference implementations and deterministic verifier scripts.
- Calibrate task difficulty using standard Terminal-Bench run configurations.
- Participate in a 4-layer human quality control process.
- Identify failure points where AI models struggle with multilingual inputs.
View Full Description & ApplyYou'll be redirected to the employer's site
