cat ./about.md

About

Brief

I graduated from the Indian Institute of Technology Jodhpur, majoring in CS. My research centers on long-term AI safety and mechanistic interpretability, and understanding how representations form, move, and change inside models.

I lead the technical research wing at Safety and Alignment Research, India, where we're currently field-building India's technical AI safety. Along the way, I've also worked at UofT, Thoughtworks AI Labs, CDA @ UIUC, IAB Lab @ IIT Jodhpur, and CERN engineers.

I am an avid Wordler, (try to) play Chess (@veeraraju_e), watch Cricket, and love Pop and Indie Rock. I'm an ISTJ-A type.

TL

  1. Jinesis Lab, UofT [External Collaborator]

    interp that generalizes.

  2. SAAR-India [Co-Founder]

    technical research head. building and guiding AI safety research.

  3. CSHL [RA]

    [discontinued].

  4. Thoughtworks AI Labs [Research Intern]

    fine-grained incompleteness evaluation of synthetic summaries at test-time.

  5. Image Analytics and Biometrics Lab [RA]

    privacy-preserving machine [un]learning for multi-modal systems.

  6. University of Illinois Urbana-Champaign [REU]

    foundation models for livestock images.

  7. Fluxgen Technologies [ML Intern]

    unsupervised anomaly detection for industrial water plants.

  8. IIT Jodhpur: B. Tech in Computer Science.

    gpa: 9.33/10.

Elsewhere

github
Veeraraju-E
lesswrong
veeraraju-elluru [soon]
X
@VeerarajuE [preferred]
linkedin
veeraraju-elluru