cv
Curriculum Vitae
Education
B.Tech in Computer Science (AI Specialization) 2022 — 2026
Manipal Institute of Technology, Bengaluru
Experience
Research Intern Jan 2026 - Present
IISc Bengaluru
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." ICLR Re-Align Workshop, 2026. [Paper] [Code]
S. Venkatesh, A. M. Kurapath, T. Melkote. "Large Language Models are Algorithmically Blind." Preprint Under Review. [Paper] [Code]
S. Venkatesh. "Architecture, Not Scale: Circuit Localization in Large Language Models." Preprint Under Review.
Research
Do LLMs Actually Feel Happy for You? — A mechanistic look at how LLMs process emotional context. [Blog]
Is Alignment Faking Generalizable? — Analyzed cross-architecture transfer of adversarial prompts in Transformer and MoE models. [Code]
Representational Asymmetry in LLMs — A systematic imbalance between a model’s capacity to describe processes and its capacity to actually simulate them. [Blog]
Prisoner's Dilemma in LLMs — Ran experiments across three different LLMs with personality variations to study cooperation and behavioral divergence. [Blog]
Projects
anada — A lightweight, terminal-first note-taking tool with Markdown support and bi-directional linking. [PyPI]
mlboardkit — A library for streamlining ML workflows through utilities for data analysis, model training and evaluation. [PyPI]
QueryMind — An AI agent for natural language to SQL query translation via MCP. [Code]
Achievements
- $700 BlueDot Impact grant for CoT faithfulness research
- $1,500 Cohere Labs Catalyst Grant
- BlueDot Impact Technical AI Safety Course
- Amazon ML Summer School'26
- AWS AI&ML Scholarship 2026
Volunteering
Reviewer — COLM 2026, ACL TrustNLP 2026, ICLR Re-Align and CAO Workshops 2026