# zeynep altun

zeynep altun is a remote worker on Himalayas, LLM Personalization & Multilingual Evaluation at Metis Project, based in Turkey.

Source: https://himalayas.app/@zeynepaltun

```text
AI Evaluation Specialist at RWS TrainAI, evaluating LLM responses through ranking, preference testing, and safety assessment.
```

| Detail | Value |
| --- | --- |
| Availability | Looking for a job |
| Location | Turkey |
| Authorized to work in | Turkey |
| Salary expectations | 400k+ TRY |
| Job categories | AI Evaluation Specialist, Data Annotator, Localization Specialist, Translator, Business Owner, 3d Designer, Graphic Designer |
| Skills | LLM Evaluation, Response Ranking, Preference Testing, Rubric Based Scoring, Rationale Writing, Search Relevance, Search Intent Analysis, Query Validation, Linguistic Evaluation, Translation Evaluation, Content safety review, Policy Compliance, Data Annotation, Data Validation, Turkish Localization |

## About

```text
At RWS TrainAI, I contribute to LLM training and evaluation projects, including response ranking, preference testing, safety assessment, and instruction-following analysis. I write structured justifications for scoring decisions within detailed project guidelines.

Across the Metis Project and OneForma, I evaluate multilingual responses and Turkish–English translations for relevance, reasoning, fluency, and accuracy. My sociology background informs my attention to analytical reasoning and bias, while my work also includes AI data annotation, running PubKA, and freelance 3D and graphic design.
```

## Experience

### LLM Personalization & Multilingual Evaluation (current)

Metis Project. Jan 2026 - Present

```text
Evaluated model responses with a focus on personalization quality, contextual relevance, and reasoning depth. Conducted side-by-side comparisons and produced structured rationales to justify preference decisions.
```

Skills: LLM-Evaluation, Personalization, Multilingual-Evaluation, Side-By-Side-Comparison, Rationale-Writing

### Linguistic Evaluation & Translation Review (current)

OneForma. Jan 2024 - Present

```text
Performed paragraph-level multi-grading for Turkish–English translations, assessing fluency, semantic accuracy, structural coherence, and overall naturalness. Conducted acceptability scoring using structured evaluation criteria across diverse text types.
```

Skills: Translation-Evaluation, Linguistic-Assessment, English-Turkish-Translation, Acceptability-Scoring, QA-Guidelines

### LLM Evaluation Specialist (current)

RWS TrainAI. Jan 2024 - Present

```text
Contributed to diverse LLM training and evaluation projects including response ranking, comparative preference testing, safety assessment, and instruction-following analysis. Provided clear, structured justifications for scoring decisions while working within detailed project guidelines.
```

Skills: LLM-Evaluation, Response-Ranking, Preference-Testing, Safety-assessment, Instruction-Following-Analysis, Rationale-Writing

### Founder & Owner (current)

PubKA. Jan 2023 - Present

```text
Founded and manage an independent bar business, overseeing operations, budgeting, branding, supplier coordination, and marketing communication.
```

Skills: Business-Management, Budgeting, Branding, Supplier-Coordination, Marketing-Communications

### AI Evaluation & Data Annotation Specialist (current)

Remote. Jan 2022 - Present

```text
Worked on large-scale AI projects involving query creation, annotation, validation, and response evaluation. Maintained consistency across evolving guidelines and complex edge cases.
```

Skills: Data-Annotation, Query-Creation, Validation, response-evaluation, Guideline-Adherence

### Freelance 3D & Graphic Designer (current)

Self Employed. Jan 2018 - Present

```text
Deliver creative projects for diverse clients, balancing artistic direction with structured revision cycles.
```

Skills: 3D-Design, Graphic-Design, Adobe-Creative-Suite, Blender

### Customer Relations Specialist (current)

Enofis. Jan 2016 - Present

```text
Manage structured communication workflows and resolve complex client issues systematically.
```

Skills: Client-Relations, Communication-Skills, Issue-Resolution

### Transcription & Academic Documentation

Self Employed. Jan 2018 - Dec 2019

```text
Transcribed long-form academic interviews and seminar recordings with high accuracy and structural consistency. Preserved meaning, tone, and contextual nuance while adhering to strict formatting standards.
```

Skills: Transcription, Academic-Documentation, Accuracy, Formatting

## Education

### Hacettepe University

Bachelor of Arts, Sociology

```text
Bachelor of Arts in Sociology from Hacettepe University.
```

## Tech stack

- Google Sheets
- Microsoft Excel
- Blender

To contact zeynep, message them from this profile with a Himalayas employer account: [Hire on Himalayas](https://himalayas.app/hire).

## People also viewed

- [Serkan User](https://himalayas.app/@bindalserkan): Linguistic Annotator, Crowdgen
- [ÖZLEM KARAYAZICI](https://himalayas.app/@zlemkarayazici): AI Language Evaluation Specialist, Freelance
- [Begüm Türkmenoğlu](https://himalayas.app/@begmtrkmenolu): AI Prompting & Data Strategy Assistant, MetaCampus
- [Burak Yalçın](https://himalayas.app/@burakyaln): AI Data Annotator & Turkish Specialist, RWS Group
- [Serra User](https://himalayas.app/@serrauser): AI Language Specialist & Data Annotator, Welocalize, RWS & OneForma
- [Nazmiye Er](https://himalayas.app/@nazmiyeer): AI Data Annotation & AI Evaluation Projects, Freelance
- [Yelda Özgezerim](https://himalayas.app/@yeldazgezerim): Freelance AI Data Annotation, Quality Evaluation & Localization Specialist, Freelance
- [Emre Erkin](https://himalayas.app/@emreerkin): Bilingual AI Generalist, DataAnnotation
- [Selen Karakoyun](https://himalayas.app/@selenkarakoyun): Lead AI Editor / AI Quality Team Lead, Yandex
- [Burak Kaya](https://himalayas.app/@burakkaya): AI Project Contractor, Handshake AI