Resume

Engineering Summer Analyst · Dallas, TX

• — Built and deployed a production-ready full-stack agentic platform used internally at Goldman Sachs for Anaplan model-sync analysis, reducing reviewer effort by 67% through AI-generated risk and downstream-impact summaries.
• — Implemented Java/Spring Boot services and a React/TypeScript frontend with a hybrid parser for 20+ report section types, combining deterministic extraction with LLM-generated summaries, risk signals, and impact analysis.
• — Built a production RAG pipeline on OpenSearch with BM25 across 4 model-context chunk types, persisting source reports in DynamoDB and generated insights in AWS S3 for durable, repeatable retrieval.
• — Delivered a 10x speedup in AI enrichment by parallelizing per-section retrieval and LLM calls with Java virtual threads and semaphore-gated concurrency, with centralized authentication, rate limiting, retries, and audit logging.

Software Engineer Intern · Remote

• — Owned the agentic market-research workflow behind Scend's M&A platform, turning natural-language market theses into structured research on growth drivers, key players, consolidation trends, and acquisition targets.
• — Built the production data-acquisition layer with Python, Node.js, and Firecrawl, orchestrating web discovery across 5 private-market entity types and normalizing results covering 189K+ companies and 14K+ investors.
• — Hardened the research pipeline across 125K+ enrichments with structured-output validation, result filtering, deduplication, response caching, and PostgreSQL-backed persistence.

NSF REU Researcher · Dallas, TX

• — Selected for a competitive NSF REU focused on agentic AI and software security research.
• — Developed MAVUL, a multi-agent vulnerability detection framework using ReAct, Reflexion, and evaluation agents that collaborate, critique, and refine security findings.
• — Evaluated MAVUL on 879 real-world C/C++ vulnerable code pairs from PrimeVul against GPTLens, VulTrial, and GPT-4o.
• — Published "MAVUL: Multi-Agent Vulnerability Detection via Contextual Reasoning and Interactive Refinement" at the IEEE TPS 2025 Conference.