Tech Stack

Description

You will advance Smartcat's translation platform by improving benchmarks, working on NER and word alignment, building automatic translation quality scoring systems, and setting up infrastructure for self-hosted solutions. Your work will power critical features for enterprise clients.

Requirements

• Evaluation engineering: translate product features into measurable use cases, build benchmarks, design rubrics, run A/B tests
• Data fluency: own end-to-end dataset pipelines with versioning and auditability
• Classical NLP foundations: understand MT/search text normalization and core matching approaches
• LLM operations: design prompts, build filters, generate synthetic data, select and route providers
• Practical production engineering: write lightweight services with monitoring, reliability, scalability

Responsibilities

• Develop and improve benchmarks for translation problems
• Work with NER, word alignment, automatic translation quality scoring system, and other problems
• Set up infrastructure for self-hosted solutions