Open to workAI-readable

Vikranth
Reddimasu

I design and build agentic AI systems end‑to‑end.

Resume ↗

Clifford Attractor

A chaotic system where deterministic equations produce infinite complexity.

x = sin(a·y) + c·cos(a·x)

y = sin(b·x) + d·cos(b·y)

a = 0.000

b = 0.000

c = 0.000

d = 0.000

Clifford Attractor

Projects

View all →

Arya: Beating the OfficeQA Benchmark

→

Set the OfficeQA accuracy record (72.0%) in Sentient Labs Arena Cohort 0. Solo build, one 6.3 KB system prompt, no MCP servers, no custom agent code.

PythonJinja2OpenHands-SDKGooseMinimax M2.5OpenRouterDocker

Pac-Man AI: From Reinforcement Learning to World Models

→

A PPO agent learns to play Pac-Man, then an RSSM world model learns to dream the game, and a dream agent learns to play entirely inside those dreams.

PythonPyTorchPPORSSMNumPyMPS

WealthAgent: Multi-Agent AI for Financial Analytics

→

Multi-agent AI system using LangGraph and Claude for financial analytics and trade cost analysis.

PythonLangGraphAnthropic ClaudeFastAPIReactPostgreSQLDocker

MacFleet: Distributed ML for Apple Silicon

→

Pool Apple Silicon Macs into a distributed ML training cluster with auto-discovery, adaptive compression, and thermal-aware scheduling.

PythonPyTorchMLXgRPCmDNSRing AllReduce

Offline Notebook LM

→

Ask questions about your own documents and get answers, entirely offline. No cloud, no data leaving your machine.

PythonElectronReactFastAPIChromaDBsentence-transformers

GAN for MNIST Synthesis

→

Generative Adversarial Network trained on MNIST and deployed as a live demo on HuggingFace Spaces.

PythonPyTorchGradioHuggingFace SpacesDocker

Skills

AI & ML

Generative AIAgentic AILLMs (Claude, OpenAI, Llama)RAGText2SQLLLM Fine-tuning & DistillationDistributed Training (DDP, DeepSpeed)TransformersNLP

Frameworks

LangGraphLangChainLlamaIndexPyTorchTensorFlowFastAPIReactPydanticWebSockets

Languages

PythonSQLRTypeScriptBash

Databases & Cloud

PostgreSQLChromaDBPGVectorDockerCI/CDGitHub ActionsHuggingFace Spaces

Data & Visualization

PandasNumPyPlotlyStreamlitJupyteryfinance

Education

M.S. in Data Science

2024 — 2026

University of Maryland — College Park

GPA: 3.85

Deep LearningAdvanced Machine LearningNatural Language ProcessingBig Data SystemsPrinciples of Machine Learning

B.Tech in Artificial Intelligence & Data Science

2020 — 2024

VVIT (Vasireddy Venkatadri Institute of Technology) — Guntur, India

GPA: 3.6/4

Probability & StatisticsMachine LearningBig Data AnalyticsDesign & Analysis of AlgorithmsData StructuresAI Tools & TechniquesAutomata TheoryOperating Systems

Beyond the Code

View all →

Leadership, workshops, publications, and the experiences that shaped how I think about building things.

Stanford Silicon Valley Meet-up

→

March 2023

Invited to Stanford University as a University Innovation Fellow for the Silicon Valley Meet-up, connecting with fellows and innovators from across the globe.

University Innovation FellowsStanfordLeadershipInnovation

Design Thinking Workshops

→

2023 — 2024

Co-facilitated Design Thinking workshops at multiple universities as a UIF team, impacting over 5,000 students through hands-on sessions on empathy, ideation, and prototyping.

Design ThinkingWorkshopsEducationLeadership

Change Forward Journal — Editorial Board

→

2022 — 2023

Served as Editorial Board Member for Stanford UIF's Change Forward Journal 3rd edition and authored two published articles on innovation in higher education.

Stanford UIFPublicationsEditorial BoardWriting

Zero Sols

→

2023 — 2024

Founded a startup providing web development and UI/UX design services for local businesses and student organizations.

StartupWeb DevelopmentUI/UXEntrepreneurship

Resources

Frameworks and methodologies that shape how I think and build.

The Golden Circle

→

Simon Sinek's framework for starting with 'Why', and how it shapes every project I build.

FrameworkLeadershipStrategy

Design Thinking

→

A human-centered approach to problem-solving that starts with empathy and ends with tested prototypes.

MethodologyUXProblem Solving

About

I'm Vikranth. MS Data Science at UMD, originally from India.

I build agentic AI systems end to end, prompts, routing, backend, frontend, deploy. Every project on this site is something I owned from the first commit.

What I care about is the part where a model gets delivered through an interface that real people use. The model is the easy part now. The interface around it is where the work lives. I want to be on a team that ships to production and measures its work by whether anyone actually adopted it.

I trust my taste, I move fast.