
MS CS @ Rutgers | AI/ML Engineer | Building semantic search, RAG & LLM systems | Open to Summer 2026 Internships
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
MS Computer Science Student
Data Scientist
June 21, 2026 – Present
semantic-search
May 10, 2026 – Present
Two-stage semantic search: bi-encoder + cross-encoder reranker on MS MARCO. NDCG@10: 0.692, +143% over BM25.
View ProjectRedirectIQ-WebFrameworksComparison
April 27, 2026 – Present
RedirectIQ-WebFrameworksComparison — repository
View ProjectVeritasAi-News-Aggregator-Agent
April 26, 2026 – Present
Real-time AI news aggregator agent with multi-source scraping, relevance ranking, and LLM-powered summarization.
View Projectvouch
April 4, 2026 – Present
Cross-party AI agent trust layer using Auth0 Token Vault and LLaMA 3.3 70B for secure credential delegation.
View ProjectQuantVision
March 21, 2026 – Present
PPO reinforcement learning agent for trading strategy optimization. Evaluated on Sharpe Ratio, Sortino Ratio across 2008/2020/2022 market regimes.
View ProjectVtrack-Traffic_Analysis_System
March 12, 2026 – Present
Real-time traffic analytics using YOLOv8 + ByteTrack for multi-object detection, tracking, and speed estimation.
View ProjectCultural Fit Analysis
The candidate's extensive list of personal projects, particularly those involving cutting-edge AI/ML technologies (LLMs, advanced search, reinforcement learning, computer vision), demonstrates a strong passion for the field and a continuous learning mindset. This aligns well with a culture that values innovation, self-improvement, and hands-on problem-solving. The breadth of technologies used (Python, JavaScript, Docker, Jupyter Notebook) also suggests versatility. The target role of Data Scientist is well-aligned with the technical focus of the projects.
Soft Skills & Operational Fit
The candidate's project descriptions indicate a proactive and self-driven individual capable of tackling complex technical challenges. The diversity of projects suggests adaptability and a willingness to explore different domains within AI/ML. However, without psychometric or English test results, it is difficult to assess communication clarity, work attitude, stress handling, or team collaboration directly. The project descriptions themselves are concise but lack detailed explanations of challenges faced or solutions implemented, which could indicate a need for improved communication of technical narratives.