
TikTok · Jul 2026 · ✅ Verified by Extern
Currently an Extern @Pfizer·🟢 Open to work
I specialize in social media content and brand strategy, transforming ideas into impactful narratives.
Discover projects that showcase my skills in social media strategy and content creation, driving brand engagement.

TikTok · Jul 2026 · ✅ Verified by Extern
.jpg)
Pfizer · ✅ Verified by Extern · ⏱️ In progress
Prototype AI-powered document intelligence with Pfizer—using OCR, LLMs, and RAG to automate real enterprise PDF workflows and build a standout portfolio project.
I specialize in social media content and brand strategy, transforming ideas into impactful narratives.
I am currently an extern at TikTok, focusing on social media content and brand strategy. My passion lies in crafting engaging digital narratives that resonate with audiences and build brand loyalty.
Externships
Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship
Pfizer
Education
Duke kunshan
Applied mathematics and computational science · Class of 2029
Skills
✅ Verified by Extern
I developed a comprehensive brand strategy for All Basics Uniforms, a clothing brand based in LA, with a strong focus on TikTok. This project included extensive research on industry trends, a competitive analysis, and the creation of a strategic framework, along with a visual mood board, to enhance content creation and brand engagement on the platform.

I produced a complete brand strategy for All Basics Uniforms including a written strategy, a three-slide Canva mood board, three TikTok videos with distinct frameworks, an adapted Instagram content set, and a finalized slide deck with a recorded Loom pitch.
✅ Verified by Extern · ⏱️ In progress
Prototype AI-powered document intelligence with Pfizer—using OCR, LLMs, and RAG to automate real enterprise PDF workflows and build a standout portfolio project.
The externship prototyped AI-driven document intelligence for enterprise PDFs, combining OCR, large language models, and retrieval-augmented generation. The work reviewed LLM fundamentals, documented architecture options, and evaluated how those components integrate with OCR and RAG pipelines. Deliverables included research summaries and technical explanations of LLM behavior within
.jpg)
I analyzed a batch of vendor documents and produced a catalog of common structures and parsing obstacles, including inconsistent date formats, mixed text/images, diverse layouts, and obscure technical terminology.
Faced a set of vendor documents, I inspected file types and date formats, noted inconsistent date representations, mixed text/images, varied layouts, and obscure technical terminology, and listed specific document types and examples of parsing obstacles.