Advisor (2025)
Senior AI Engineer (2025)
Visiting AI Scientist (2024)
Visiting Researcher (2024)
Visiting AI Scientist (2023)
AI Engineer and Scientist (2020-23)
Visiting Scholar (2019-20)
PhD Student (2014-19)
AI Engineer and Scientist Lead with 5+ years industry experience (Meta AI, AI agent startup) and deep expertise in AI safety/alignment, differential privacy, federated learning, LLMs/RAG systems.
Seeking senior individual contributor, lead, or advisory roles in frontier AI labs and high-impact startups.
Recently, I worked on advanced AI agents and RAG for finance and accounting at Aktus AI. I built and productionized pipelines for classical and graph RAG (AI agents, multi-agent systems, tool use, embeddings, semantic search, vector databases) and for achieving accurate chart, graph, and long document understanding and multi-step reasoning.
I have also worked in AI safety. I published several papers recently on AI safety and alignment of LLMs and VLMs. I developed a novel LLM safety fine-tuning and representation engineering method to disrupt harmful representations and achieved up to 95% reduction in jailbreak attack success rates. I contributed to multi-modal VLM reasoning and safety benchmarks, alignment frame-works (judge-augmented SFT, on-policy learning). I have also been scientific advisor for AIM Intelligence, an AI safety pioneer, recently raising $1.3M.
Previously, I was an AI Research Scientist at Meta AI and worked on deepfake detection and developed technologies for privacy-preserving machine learning and federated learning. I created, operationalized, and delivered Green Federated Learning, a multi-year million-device work across 5 teams. I was core contributer to Opacus, an open-source library that enables training deep learning models with differential privacy (see blog posts 1 and 2), and FLSim, an open-source library for simulating federated learning systems. I published papers too.
Prior to that, I was a Visiting Researcher at University of California, Berkeley and member of the Berkeley Artificial Intelligence Research (BAIR). When I was at UC Berkeley, I contributed to Flow, an open-source deep reinforcement learning-enabled framework for simulation of autonomous and manned cars.
I earned my PhD degree in Computer Science at the University of Texas at Dallas. My work was on the intersection of Computer Systems, Edge Computing, and Machine Learning, specifically, on improving quality of service in IoT and deep learning Applications through Fog Computing. I won the UT Dallas Best Dissertation Award.