Final-year B.Tech AI student & independent AI safety researcher
Two published frameworks — ARGUS (constitutional AI security) and SHADE (multi-agent covert collusion). Builds production-grade multi-agent RAG systems, adversarial safety benchmarks, and LLM evaluation pipelines. Achieved 10× inference latency reduction in production.
About
Targeting AI safety, LLM systems, and multi-agent research roles.
Final-year B.Tech AI student and independent AI safety researcher with two published frameworks — ARGUS (constitutional AI security) and SHADE (multi-agent covert collusion). Builds production-grade multi-agent RAG systems, adversarial safety benchmarks, and LLM evaluation pipelines. Achieved 10× inference latency reduction in production.
Research interests: AI safety, principal hierarchy attacks, emergent covert coordination, efficient reasoning, mechanistic interpretability.
Experience
Programmers Trend (Internship Included)
OpenHire (AI Job-Application Agent)
Research Projects
Production and research-grade work from my resume — adversarial safety, GraphRAG, and autonomous agents.
Publications
Peer-oriented preprints and formal research outputs with verifiable DOI.
Technical Skills
Education
Velagapudi Ramakrishna Siddhartha Engineering College, Vijayawada
Narayana Junior College, Vijayawada
Viswabharathi EM High School, Gudivada
Contact
Hyderabad, India · Open to research collaborations and AI safety / LLM systems roles.
+91 9398294755