Timeline·13 entries, 2022–2026

Timeline

What happened, and when: papers, talks, jobs, a course. Where it happened is on the About page.

The places, with their plates →

2026

  1. Anaconda acquired Enkrypt AI. Continuing my AI safety and evaluation research at Anaconda as an AI Research Engineer.

    Announcement

  2. Completed the Technical AI Safety course by BlueDot Impact.

    Technical AI Safety

  3. Presenting papers at the AAAI 2026 workshops: LAMaS, AIGOV, and GCLR. Will be sharing recent work and engaging in discussions on multi-agent systems, AI governance, and graph reasoning.

    Pl. VISingapore

2025

  1. Three papers accepted to AAAI 2026 workshops: one in LaMAS (LLM-based Multi-Agent Systems), one in AI Governance (AIGOV), and one in Graphs and Complex Structures for Learning and Reasoning (GCLR).

    AIGOVGCLRLaMAS

  2. Three papers accepted to NeurIPS 2025 workshops: one at LLM Evaluation and two at Reliable ML from Unreliable Data.

  3. [ONLINE] Participated in LOGML 2025 (July 7–11), focusing on research in graph reasoning with large language models.

    LOGML

2024

  1. Three papers accepted at NeurIPS 2024 workshops: Safe Generative AI, Red Teaming GenAI, and Pluralistic Alignment

    Safe GenAIRed TeamingPluralistic

  2. Published "Increased LLM Vulnerabilities from Fine-tuning and Quantization" on arXiv

    arXiv

2023

  1. Presented a work on Efficient Homomorphic Enkryption in LLMs at AI-ML Systems 2023.

  2. Enkrypt AI A Robust Model Rights Management Solution for Secure AI Deployment got accepted in Demo Track of AI-ML Systems 2023.

    AI-ML Systems (Demo Track)

  3. Joined Enkrypt AI as Founding ML Research Engineer

    Enkrypt AI

2022

  1. Joined IISc Bangalore as Research Associate. Will be working on Neural Machine Translation for Indic Languages under the guidance of Prof. Prathosh AP.

    Pl. VBangalore

  2. Graduated from Narula Institute of Technology, Kolkata with a Bachelor of Technology in Electronics and Communication Engineering.

    Pl. IIIKolkata