Choose a background

all three respond to your cursor

Divij Chawla

student / researcher / builder

I’m a University of Washington student studying computer science and physics, focused on AI security, model evaluation, and research systems.

Most of my recent work has been around automated red teaming, safety benchmarking, trace-based evaluation, and building technical infrastructure that holds up under real use.

I’ve worked across academic research, applied AI security, and systems-heavy engineering, and I’m especially interested in problems that are both technically deep and directionally important.

Focus

AI security ML: automated red teaming, safety benchmarking, monitoring, provider-SDK agent harnesses, trace-scored evals, reproducible PyTorch pipelines, Docker, and Slurm/HPC.

Education

University of Washington

Seattle, WA

Bachelor of Science in Computer Science · Expected 2028

GPA 3.80 · Dean’s List · Pursuing Double Major in Physics

Experience

SPAR Research Fellow

Feb 2026 – Present

Supervised Program for AI Research · Remote

  • Building a safety benchmark for LLM and agent shutdownability in realistic tool-use tasks.
  • Implementing automated red-team agent harnesses and trace scoring for shutdown resistance patterns.

AI Security Researcher

Mar 2025 – Aug 2025

Walled AI · Singapore, Remote

  • Built FINRISKEVAL to measure correctness and intent alignment in finance across 1,720 profiles and 8 models.
  • Co-authored deployment playbooks covering red teaming, safety evals, intent alignment, and guardrails.

AI Research Intern

Jul 2024 – Mar 2025

University of Bristol · Bristol, UK, Remote

  • Built eval harnesses for latent alignment failures via representation backdoor attacks.
  • Measured sleeper-agent persistence and mitigation reliability under white-box and black-box settings.

Software Development Intern

Jun 2023 – Jul 2024

Emsec Private Limited · Bangalore, Remote

  • Built and operated a honeypot fleet simulating 7k+ vulnerable applications.
  • Turned attacker telemetry into labeled evidence and stronger defensive automation signals.

DSP Intern

May 2025 – Aug 2025

Emsec Private Limited · Bangalore, India

  • Optimized C++ DSP modules for high-throughput SDR pipelines and low-latency inference.

Activities

  • Lavin Entrepreneurship Program
  • Interactive Intelligence (I2), UW
  • Husky Satellite Lab

Skills

Python, C++, PyTorch, Transformers, SQL, Linux, Git, Docker, Slurm/HPC, OpenAI Agents, Google ADK, evaluation harnesses, experiment tracking.