# aryan pagaria

aryan pagaria is a remote worker on Himalayas, Software Engineering Intern at variA/Bly, based in India.

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

```text
AI research intern at variA/Bly and SpazorLabs, evaluating LLM grounding models and building agent pipelines.
```

| Detail | Value |
| --- | --- |
| Availability | Looking for a job |
| Location | India |
| Authorized to work in | India |
| Salary expectations | 132k+ INR |
| Job categories | Artificial Intelligence Intern, Software Engineering Intern |
| Skills | AI, Large Language Models, LLM Fine tuning, PEFT (Parameter Efficient Fine Tuning), LoRAs, QLoRA, 4 Bit Quantization, Model Evaluation, Uncertainty estimation, Calibration, RAG, Agent orchestration, Sequence Modeling, Transformers, GRU |

## About

```text
At variA/Bly, I fine-tune and evaluate domain-specific grounding and judge models that check AI-generated answers against source documents. I benchmark their accuracy, false-positive rate, missed errors, and latency, then calibrate scoring thresholds.

At SpazorLabs, I contribute to production-oriented LLM pipelines and AI agent systems. My work includes agent orchestration, state management, structured outputs, and evaluation for reliability.

Through my independent Modus_X research, I explore memory-efficient recurrent architectures as alternatives to attention-based context storage. I design controlled comparisons with Transformer baselines across memory retention, associative recall, language-model quality, and inference memory.

My projects include a reproducible benchmark comparing GRU and Transformer models on associative recall, and work on calibration and selective prediction for financial QA. I also fine-tuned Qwen2.5-3B-Instruct with QLoRA and built a reproducible training and evaluation pipeline.
```

## Experience

### Software Engineering Intern (current)

variA/Bly. Nov 2026 - Present

```text
Fine-tune and evaluate domain-specific grounding and judge models that verify AI-generated answers against source documents. Benchmark accuracy, false-positive rate, missed errors, and latency against existing models on fixed held-out test sets.
```

Skills: LLM-Fine-tuning, Evaluation, Benchmarking, Calibration, Regression-Testing, Python

### Artificial Intelligence Intern (current)

SpazorLabs. Sep 2026 - Present

```text
Contribute to production-oriented LLM pipelines and AI agent systems with multi-step workflows and API/tool integration. Work on agent orchestration, state management, structured outputs, and evaluation/observability for reliability.
```

Skills: LLM-Training-Pipelines, AI-Agents, Orchestration, State-Management, Structured-Outputs, Evaluation, Observability

## Education

### SRM Arts and Science College

Bachelor of Science, Artificial Intelligence. 2025 - Present

```text
Pursuing a Bachelor of Science in Artificial Intelligence, with expected graduation in 2028.
```

## Tech stack

- GitHub Actions
- NumPy
- Python
- PyTorch
- scikit-learn
- FastAPI
- Transformers
- Linux
- Git
- Docker
- SQL
- Bash
- Faiss
- Matplotlib
- AWS
- REST APIs

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

## People also viewed

- [Shaswata Biswas](https://himalayas.app/@shaswatabiswas): AI Research Intern, Planto.AI
- [Umar Imam](https://himalayas.app/@umarimam): AI Engineer Intern, Codestore Technologies
- [Aneesh Kadam](https://himalayas.app/@aneeshkadam): AI/ML Intern, OWL AI
- [Bharath Raj](https://himalayas.app/@bharathraj1): Machine Learning Intern, DLK Technology
- [Shramita Maheshwari](https://himalayas.app/@shramitamaheshwari): AI Intern, Infosys Springboard
- [Kalash Tiwari User](https://himalayas.app/@kalashtiwariuser): AI Engineer, Adya.AI
- [Parth Kulshreshtha](https://himalayas.app/@parthkulshreshtha): Associate AI Engineer, Centific
- [Anuj Pathak](https://himalayas.app/@anujpathak1): AI/ML Intern, Alfa Laval
- [Uzair meran khan User](https://himalayas.app/@uzairmerankhanuser): Founding AI Engineer, Scalric
- [Amitabh Dey](https://himalayas.app/@amitabhdey1): AI Image Preference Analyst, Internship
