# Pranay Dogra

## Pranay Dogra

Engineering student at UC Berkeley.

I study EECS and Industrial Engineering & Operations Research. I’m exploring AI safety evaluations, token-efficient AI systems, and prediction markets.

[What I’m working on ↗](https://pranaydogra.com/#research)

## Research

CURRENT / SEP 2026–PRESENT

### Dana Carney Lab

UC Berkeley Haas School of Business · Undergraduate researcher

I develop Python and PyTorch pipelines for multimodal behavioral analysis, extracting facial, vocal, and paralinguistic features from video and audio. These measures support the lab’s research on political ideology, race, and socioeconomic status.

PREVIOUS / SUMMER 2023

### Evaluating bias in LLM decisions

UC Berkeley AI Research · Student researcher

I built a 1,020-prompt benchmark to study bias in model decisions across healthcare, criminal justice, and business scenarios. I collected model choices and logits from FLAN, Vicuna, LLaMA, and LLaMA 2.

[Read the resulting paper ↗](https://pranaydogra.com/#publications)

### Research interests

I’m interested in model evaluations and benchmarks for AI safety. I’m also exploring token-efficient AI systems and prediction markets.

### Publications

IEEE ICTC 2024

### Quantifying Bias in Agentic Large Language Models: A Benchmarking Approach

A benchmark examining model decisions across race, gender, age, socioeconomic status, and political bias.

[Read on IEEE Xplore ↗](https://ieeexplore.ieee.org/document/10601938)

## Projects

IN PROGRESS

### LLM Token Efficiency

Exploring how model routing, caching, and context management affect cost and answer quality. Includes a literature review and two local prototypes; live-model evaluation is next.

[View project on GitHub ↗](https://github.com/pranayD21/llm-token-efficiency)

LLMS / STATE MACHINES

### Babel

I built a system that turns legal agreements into executable state machines for validation and scenario testing. Multiple agents share context and use validation feedback to refine the output.

[View Babel on GitHub ↗](https://github.com/neelsck/DDKT)

LLMS / TOKEN EFFICIENCY

### SLM Cascade

An inbox agent router that starts with small local models and escalates when needed. I benchmarked latency and token usage across Ollama, OpenAI, and Claude.

[View SLM Cascade on GitHub ↗](https://github.com/pranayD21/slm-agent-router)

## STAR

[calstar/STAR ↗](https://github.com/calstar/STAR)

### Space Technologies and Rocketry

UC Berkeley’s student-run rocketry team. Students design, build, and test rockets, including liquid-propellant vehicles.

- 27,326 ft · Caldera flight altitude, 2024
- 6th place · IREC 2024, 30,000-foot category[Team results ↗](https://crowdfund.berkeley.edu/project/43553)

MY WORK / AUG 2026–PRESENT

### Data acquisition software

I built C++ support for an environmental sensor board, parsing UDP packets for temperature, humidity, and pressure telemetry. I integrated the board into STAR’s configuration, data streams, and monitoring interface.

## Resume

[Open resume ↗](https://pranaydogra.com/Pranay_Dogra_Resume.pdf)[Download PDF ↓](https://pranaydogra.com/Pranay_Dogra_Resume.pdf)

EDUCATION

### University of California, Berkeley

B.S. in Electrical Engineering & Computer Science and Industrial Engineering & Operations Research

AUG 2026–PRESENT

### Software Engineer · Berkeley STAR

Built C++ support for environmental sensor telemetry, from UDP packet parsing to the data acquisition interface.

NOV 2024–AUG 2026

### Founder · CueLens

Built assistive AI for facial emotion recognition. Interviewed 50+ clinicians and users and secured partnerships with three autism clinics.

SUMMERS 2024 & 2025

### Software Engineering Intern · Mirro.ai

Created a balanced dataset of 40,000+ videos and images to reduce bias in an emotion-recognition model. Integrated the model into robotics applications.

TOOLS I USE

Python · C++ · C · Java · PyTorch · Git · Ollama · Kubernetes

Research roles are listed in [Research](https://pranaydogra.com/#research). The PDF includes the full details.

## Links

[GitHubCode and experiments↗](https://github.com/pranayD21)[LinkedInExperience and connections↗](https://www.linkedin.com/in/pranay-dogra-896b35214/)[BabelContracts as executable state machines↗](https://github.com/neelsck/DDKT)[SLM CascadeA small-model-first inbox agent router↗](https://github.com/pranayD21/slm-agent-router)[IEEE publicationQuantifying bias in agentic LLMs↗](https://ieeexplore.ieee.org/document/10601938)[CueLens in the Midpeninsula PostThe story behind the project↗](https://midpenpost.org/2025/11/18/subtitles-but-for-facial-expressions-a-bellarmine-high-seniors-journey-innovating-to-empower-individuals-on-the-autism-spectrum/)

## Contact

[pranay.dogra@berkeley.edu ↗](mailto:pranay.dogra@berkeley.edu)

[LinkedIn ↗](https://www.linkedin.com/in/pranay-dogra-896b35214/)

## Privacy

Updated September 28, 2026

### Site data

This portfolio’s code does not include advertising, analytics, tracking cookies, or a contact form. It saves your light or dark theme choice in your browser’s local storage. You can remove that preference by clearing this site’s browser data.

### Hosting

The public website is hosted on GitHub Pages. GitHub logs visitor IP addresses for security purposes. See [GitHub’s privacy statement](https://docs.github.com/en/site-policy/privacy-policies/github-general-privacy-statement).

A separate preview is hosted through OpenAI Sites on Cloudflare. Its hosting and sign-in services may process technical information, such as IP addresses, browser details, and access logs.

### External links and email

Spotify and other external links open separate websites with their own privacy policies. No Spotify player is embedded here. If you email me, I receive your address and the information you choose to send through my email provider.

### Contact

For privacy questions, email [pranay.dogra@berkeley.edu](mailto:pranay.dogra@berkeley.edu).

## Accessibility

The site supports keyboard navigation, light and dark themes, and your device’s reduced-motion setting. ASCII animations play briefly, then stop. The resume summary is available as text alongside the PDF.

If something is difficult to use, email [pranay.dogra@berkeley.edu](mailto:pranay.dogra@berkeley.edu).