Experience 💼

Harvard Medical School & Massachusetts General Hospital

Data Scientist (Boston, MA)
April 2024 – Present

Engineered scalable bioinformatics pipelines to process TB-scale multimodal data from 1500+ patient biopsies, supporting mutation discovery and ML modeling by leveraging cloud-based solutions (Google Cloud Batch, WDL, Bash)
Optimized storage workflows by automating ad hoc usage reports, coordinating data migration with external collaborators on HPC systems, and leveraging tiered Google Cloud Storage classes to cut long-term costs by 20%
Containerized Linux-based mutation detection tools using Docker on SLURM clusters and GCP to ensure cross-platform reproducibility of genomics analyses, enabling portable workflows with standardized results
Developed real-time interactive dashboards with Plotly Dash to unify clinical findings with public genomics databases, enhancing data-driven decision making and advancing cancer research

Data Engineer (Boston, MA)
February 2025 – July 2025

Constructed an ETL pipeline to automate patient-to-trial matching, boosting screening efficiency by 42% through NLP-based parsing of EHR data, creation of embeddings using ClinicalBERT, and retrieval-augmented generation (RAG)
Optimized backend infrastructure costs by 30% and enabled frontend integration by deploying REST APIs for patient and trial data access using serverless cloud platforms (AWS Lambda, API Gateway, Firebase Auth, Pulumi)
Designed relational schemas in PostgreSQL to manage patient data, trial evaluations, audit logs, reducing query time by 22% through strategic data modeling, indexing, and caching
Implemented CI/CD workflows with GitHub Actions to automate unit testing, infrastructure provisioning, and codebase deployments, accelerating the software development life cycle (SDLC)

Clinical Data Analyst (San Diego, CA)
April 2024 – September 2024

Migrated and transformed OMOP-standardized EHR data for 10,000+ patients across 35 hospitals into analytics-ready schemas using SQL and BigQuery, facilitating the training of clinical AI models
Engineered clinical and social determinants of health features (MELD score, ICD-10 codes) to predict 30-day readmission of cirrhosis patients using a random forest classifier, achieving an AUC of 0.87

Undergraduate Researcher (San Diego, CA)
April 2023 – April 2024

Developed a GenePattern Notebook submodule to compute p-values and FDRs across 70+ cell types and 50+ gene sets from scGSEA data by simulating null distributions through subsampling
Implemented parallel processing in Python and R scripts to enhance statistical testing of scGSEA data, achieving a 92% reduction in runtime validated across multiple AWS EC2 configurations

Bioinformatics Intern (San Diego, CA)
June 2023 – September 2023

Integrated Azure Batch and Blob services into DSL-2 Nextflow pipelines for scalable and automated FASTQ alignment, BAM quantification, and bigWig generation of transcriptomic data
Containerized Conda environments to enable reproducible benchmarking of bioinformatics tools for intron retention detection, aiding the design of antisense oligonucleotides to treat haploinsufficiency diseases

Undergraduate Researcher (San Diego, CA)
June 2022 – March 2023

Utilized DESeq2 for RNA-seq analysis, identified top 200 differentially expressed genes, and elucidated their functional roles in CD40-treated vs. untreated TNBC mice through GO enrichment analysis
Leveraged Seurat and inferCNV for scRNA-seq analysis, immunophenotyped 18+ cell groups from aPD1/aCTLA4-treated vs. untreated TNBC mice by examining gene profiles and copy number variations
Performed pseudotime analysis using Monocle3 and Slingshot on liver metastases in TNBC mice, effectively modeling differentiation patterns of immune cells

Frontend Engineer (San Diego, CA)
November 2021 – June 2022

Utilized React-Bootstrap to build a form for future TSE applicants and manage data of past applicants
Coordinated with a team of 5 web developers and 3 UI/UX designers to build components of the form using HTML, CSS, JavaScript