cv
Curriculum Vitae
Education
Bachelor of Technology, Computer Science 2022 — 2026
Manipal Institute of Technology, Bengaluru
Experience
Research Mentor Sep 2026 - Present
SPAR Research
Research Fellow Jul 2026 - Present
LASR Labs
Research Intern May — Oct 2025
IIIT Hyderabad
AI Fellow Jul - Sep 2024
Fellowship.ai
Project Intern May - Jul 2024
Infosys
Publications
S. Venkatesh, A. M. Kurapath. "On the Non-Identifiability of Steering Vectors in Large Language Models." Representational Alignment Workshop at ICLR 2026. [Paper]
S. Venkatesh. "Architecture, Not Scale: Circuit Localization in Large Language Models." Mechanistic Interpretability Workshop at ICML 2026. [Paper]
S. Venkatesh. "Negative Before Positive: Asymmetric Valence Processing in Large Language Models." Mechanistic Interpretability Workshop at ICML 2026. [Paper]
S. Venkatesh, T. Jiralerspong, F. Kondrup. "Where Empathy Goes Wrong: Emotional Appeals Compromise AI-to-AI Oversight." Agents in the Wild Workshop at NeurIPS 2026. [Paper]
S. Venkatesh, A. M. Kurapath, T. Melkote. "Algorithmic Blindness in Large Language Models: A Calibration Study of Performance Prediction." AI Measurement Science Workshop at COLM 2026. [Paper]
S. Venkatesh. "Repeated-Token Counting Reveals a Dissociation Between Representations and Outputs." Preprint. [Paper]
Projects
Sandbagging Evaluation in LLMs — Inspect-based evaluation testing whether frontier LLMs sandbag after discovering a hidden threshold under different framings. [Code]
Inverse Scaling in CoT faithfulness — Showed unfaithfulness in larger LLMs is a capability artifact after controlling for accuracy. [Code]
Diffing for Model Spec Midtraining — Studied whether model diffing recovers a value installed during model spec midtraining in Llama 3.1 8B. [Code]
nanoKimi — An implementation of Kimi-K2 with Muon optimizer and latent attention mechanism. [Code]
MCRAG — A multi-LLM code generation and review system with a generator and two critics. [Code]
Achievements
- $13,500 Manifund grant for AI control research
- $5,000 Tinker grant for model persona research
- $3,700 BlueDot grant for CoT faithfulness research
- Amazon ML Summer School'26
- AWS AI&ML Scholarship 2026
Volunteering
Reviewer — COLM 2026, ACL TrustNLP 2026, ICLR Re-Align and CAO Workshops 2026