# Alyssa Liana

Alyssa Liana is a remote worker on Himalayas, Quality Assurance Evaluator & AI Research Specialist at Outlier AI, based in United States.

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

```text
AI evaluator at Outlier AI auditing LLM agent failures and shaping reproducible evaluation benchmarks.
```

| Detail | Value |
| --- | --- |
| Availability | Looking for a job |
| Location | United States |
| Authorized to work in | United States |
| Salary expectations | 65k+ USD |
| Job categories | AI Evaluator, AI Researcher, Research Assistant |
| Skills | LLM Evaluation, LLM Agents, Human Computer Interaction, Behavioral Modeling, Benchmark Design, Error Analysis, Model Evaluation, Experimental Design, A B Testing, Causal Inference, Statistical Significance, Ablation Studies, Qualitative Synthesis, Rubric Based Scoring, Provenance |

## About

```text
At Outlier AI, I audit and rank complex LLM outputs against rubrics for reasoning, safety, and goal compliance. I document agent failure modes and design error-classification taxonomies for model alignment and benchmarking.

At the University of Alaska, I develop reproducible Python pipelines to simulate multi-turn, goal-oriented web browsing. I compare synthetic clickstream patterns with real-world user interaction traces.

I also conduct significance testing and ablation studies to examine how prompt variations and context constraints affect model behavior.

Earlier, as a Research & Academic Content Assistant at University of Alaska Anchorage, I synthesized qualitative evaluation reports and checked research data against original empirical sources. My Ph.D. work focuses on simulated user exploration and behavioral calibration in autonomous web agents.
```

## Experience

### Quality Assurance Evaluator & AI Research Specialist (current)

[Outlier AI](https://himalayas.app/companies/outlier-ai). Jan 2025 - Present

```text
Audit, evaluate, and rank complex LLM outputs based on strict rubrics for reasoning, safety, and goal compliance. Identify and document failure modes, including hallucinations, tool execution loops, and logical fallacies in multi-step agent trajectories.
```

Skills: LLM-Evaluation, Error-Analysis, Rubric-Based-Scoring, Python, Model-APIs, Provenance

### Graduate Research Assistant (current)

University of Alaska. Aug 2024 - Present

```text
Develop reproducible Python pipelines for simulating multi-turn goal-oriented web browsing behavior. Formulate baseline metrics comparing synthetic clickstream distributions with real-world user interaction traces.
```

Skills: Python, PyTorch, NumPy, Pandas, scikit-learn, Selenium, Playwright, Statistical-Testing, Ablation-Studies

### Research & Academic Content Assistant

University of Alaska Anchorage. Sep 2023 - May 2024

```text
Synthesized qualitative evaluation reports for department manuscripts and research datasets. Maintained database integrity by cross-referencing qualitative data entries against original empirical source documents.
```

Skills: Qualitative-Analysis, Data-Management, Documentation, Research-Support

## Education

### University of Alaska

Ph.D., Computer Science / Human-Computer Interaction

```text
Pursuing a Ph.D. in Computer Science with a focus on Human-Computer Interaction, expected graduation in May 2028.
```

### University of Alaska Anchorage

Master of Arts, Philosophy

```text
Completed a Master of Arts in Philosophy with a focus on Cognition and Logic in May 2024.
```

### University of Alaska Fairbanks

Bachelor of Arts, Philosophy

```text
Completed a Bachelor of Arts in Philosophy in May 2022.
```

### CITI Program

Ethical Research & Data Evaluation (CITI Program Certified), Research Ethics

```text
Certification in Ethical Research and Data Evaluation, Social & Behavioral Modules.
```

### QSR International

Advanced Quality & Qualitative Analysis Certification, Qualitative Analysis

```text
Certification in Advanced Quality and Qualitative Analysis.
```

## Tech stack

- Selenium
- Jupyter
- NumPy
- Pandas
- Python
- PyTorch
- scikit-learn
- Git
- Hugging Face
- Playwright
- OpenAI API

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

## People also viewed

- [ROBINSON OJWANG](https://himalayas.app/@robinsonojwang): Generative AI Specialist, Innodata
- [valezquez Daymaris](https://himalayas.app/@valezquezdaymaris): AI Trainer / Evaluation Analyst, Scale AI
- [Livia Maia](https://himalayas.app/@livmaia): AI/ML Evaluation Specialist, Google
- [Griffins Ochieng](https://himalayas.app/@griffinsochieng1): AI Data Annotator & QA Specialist, Metriq AI
- [Mark Nderitu](https://himalayas.app/@marknderitu): AI Evaluator & Research Analyst, NorthStar AI Research Group
- [joseph esposito](https://himalayas.app/@josephesposito1): AI Data Trainer & Model Evaluator, Self Employed
- [BRANDON TAFT](https://himalayas.app/@brandontaft): Senior Data Annotation Specialist, Remote AI Data Projects
- [Social Hubb](https://himalayas.app/@socialhubb): AI Evaluation Specialist & RLHF Annotator, Outlier AI / Scale AI
- [Mitchell Kinyua](https://himalayas.app/@mitchellkinyua): AI Evaluation & Research Specialist, Freelance Platform Networks
- [Clement Ejiobih](https://himalayas.app/@clementejiobih): Freelance AI Trainer & Evaluator, Independent Contractor