Accelerated CS @ Boston University, graduating a year early. I build production systems as the sole engineer — a degree planner used by ~900 students, and a nonprofit's entire 250+ endpoint platform. Alongside that, I contribute to the LLM inference stack (vLLM, llm-d, KServe, InstructLab): my niche there is finding the paths a new feature quietly fails on.
CTO & Sole Engineer Honor Society of Cinematic Arts Multi-tenant platform · 250+ endpoint API · live across 15+ chapters & 150+ members |
SWE Intern BU Spark! Harvard Herbaria OCR confidence layer (FastAPI) · micro-credentialing platform · BU Spark!'s project showcase (sole author, live at atlas.buspark.io) |
SWE Intern Doro (Local Treasure) TikTok OAuth, Stripe checkout & moderation tooling (Django/DRF) |
Research Assistant BU CISS Financial markets × geopolitical uncertainty · Python data workflows |
Previously — AI & Software Engineer Intern @ HireBuddy · Lead Software Engineer @ Hack4Impact BU
I contribute to vLLM, llm-d (a CNCF sandbox distributed LLM inference stack founded by Red Hat, Google Cloud, IBM Research, CoreWeave and NVIDIA), KServe, and Red Hat's InstructLab. Contributions now also span Grafana, Redis (node-redis — merged fix), Prisma, MLflow, Keras, Datadog, and the Model Context Protocol registry — same method everywhere: reproduce the failure with executed evidence before proposing the fix.
53 pull requests across 21 repositories in 15 organizations |
17 merged — including 12 into llm-d-benchmark reviewed and approved by two separate core maintainers, plus fixes merged into vLLM and node-redis |
9 defects found and filed against a newly released no-Kubernetes deployment path, 6 reproduced live with tracebacks |
~30 substantive code reviews and root-cause analyses on other contributors' PRs and issues |
What I am actually useful for: running a brand-new feature on a machine its maintainers do not have, a clean macOS laptop with no cluster and no GPU, and finding the paths where it reports success while doing nothing. That produced nine issues against one feature, including a container name collision that let one deployment's teardown destroy a sibling deployment's running containers.
Reviewing counts too. On someone else's pull request I found that a proposed dependency pin would fail the project's own version comparison, so every install would re-run the installer and silently overwrite the user's kubectl binary. Proven by running the project's own function against the proposed value.
Also opened fixes merged into the Kubernetes SIG's gateway-api-inference-extension (3 merged, 1 draft) and open PRs against SGLang.
|
Autonomous banks, central banks & payment rails (RTGS/ACH/SWIFT/CLS/DTCC), systemic-risk analysis, crisis replay & a hand-written regulatory DSL.
|
Degree planning for ~900 BU students across 6,000+ courses. Requirement-validation engine, vector-embedding semantic recommender replacing a quota-limited LLM at zero marginal cost, Redis layer at ~81% hit rate over 66k+ lookups.
|
|
The production system of record behind my CTO role — member lifecycle, payment-gated resources, evaluation forms & a film festival, with per-chapter tenant isolation.
|
Built the AI candidate-sourcing engine (Elasticsearch-DSL over CoreSignal) — tripled candidates surfaced per search (100 → 300) — and co-built a GPT-4o-mini pre-screening engine scoring across 10 evidence-backed dimensions.
|
OCR confidence-preservation layer for a specimen-digitization ML platform — a versioned per-field certainty envelope surfacing Azure vision-OCR to reviewers, plus SSRF + authorization hardening. Client-owned (BU Spark!) — no public repo |
Owned the SE-Chem badge-authoring wizard end-to-end — decomposed an 843-line page into components, killed a stale-closure bug, and batched Client-owned (BU Spark!) — no public repo |
🏆 InstructLab KnowFlow LangGraph + MCP agentic workflow automating InstructLab contributions — accepted for upstream evaluation. |
🥈 Cognify AI course & career advisor over 6,000+ BU courses with Gemini recommendations & skill-gap analysis. |
⚛️ Quantum Explorer Interactive 3D quantum-entanglement platform with AI-powered concept grading. |
%%{init: {'theme':'base','themeVariables':{'primaryColor':'#171F33','primaryTextColor':'#E6EDF3','primaryBorderColor':'#14B8A6','lineColor':'#10B981','fontSize':'14px'}}}%%
flowchart LR
UI["Frontend\nReact · Next.js · Three.js"] --> API["APIs\nFastAPI · Flask · Express · DRF"]
API --> AI["AI Layer\nLangGraph · MCP · embeddings · TF-IDF retrieval"]
API --> DATA[("Data\nPostgres · Redis · Elasticsearch")]
AI --> DATA
API --> INFRA["Infra\nDocker · AWS · Vercel · Railway"]
DATA --> INFRA
