Software Engineer & AI/ML Researcher

Imaan Soltanalipour

Studied Computer Science at UCLA and Moorpark College, building reliable AI/ML systems end to end, from generative models to full-stack apps. Researcher at the Aharoni Lab; former intern at Amgen and NASA Langley NCAS Graduate.

View work Résumé

Featured projects

A few things I've built. See all on the projects page.

All projects

Found Sound Orchestra

Live

A hackathon project: a generative-music web app that maps camera-captured objects to instruments with Gemini Flash, composes full pieces with Lyria Pro, and generates music videos with Veo 3.0 — with a live FFT stem-mixer.

Gemini
Lyria
Veo 3.0
Python
Web Audio

Details Visit live site

Flow-Matching Driving Planner — Trajectory-Representation Ablation

Ablated four trajectory representations (Cartesian waypoints, Frenet, velocity, acceleration) inside a vendored NeurIPS-2025 flow-matching planner (Tan et al.), training each variant on 1.5k-scenario subsets drawn from an 80k-sample nuPlan-mini cache. On open-loop ADE (average displacement error), Cartesian waypoints performed best — roughly 5x lower error than the velocity- and acceleration-based representations (4.19 m vs ~22 / 20 m).

PyTorch
Flow Matching
Autonomous Driving
nuPlan
Research

Details Code

BetBat — Real-Time Social Prediction Market

Live

A real-time prediction-market app (Next.js 16 / React 19 / TypeScript / Firestore) built over a 6-week Agile project, with transaction-safe coin economics, an LLM (OpenAI gpt-4o-mini) that structures free-form bets into verifiable yes/no markets, and a market-resolution state machine.

Next.js
React
TypeScript
Firestore
OpenAI

Details Visit live site Code

LLM Knowledge Base / RAG

An offline-first, event-sourced knowledge system: it captures text (a global hotkey on Windows), organizes it with a local LLM (Ollama) into a semantically linked Obsidian Markdown vault, and auto-generates dependency-ordered plans via a Kahn topological sort. The platform-agnostic core runs fully offline.

Ollama
RAG
MCP
Python
Event Sourcing

Details Code

Agentic Meta-Harness

A meta-harness that wraps an AI coding agent and enforces eight deterministic, fail-closed engineering gates (build, hygiene, layout, format, lint, typecheck, tests, security) via Claude Code hooks. v0 governs Python projects, with a per-language/per-harness seam designed to extend to other stacks and agents.

Claude Code
CI Gates
ADRs
Python
Agentic

Details Code

Research

Selected publications

Peer-reviewed work and preprints.

All publications

STIMscope: centimeter-scale all-optical imaging and patterned optogenetic manipulation at single-cell resolution

Hamid Chorsi , Saray Soldado-Magraner , Yan Jin , Imaan Soltanalipouryekesammak , Alex Zheng , Dejan Marković , Daniel H. Geschwind , Peyman Golshani , Dean V. Buonomano , Daniel Aharoni

bioRxiv, 2026

DOI PubMed

3MagicLabs

My research & engineering lab

3ML About 3MagicLabs — overview and information on the lab. borromeanRings Agentic meta-harness — deterministic, fail-closed quality gates over any AI coding agent. Grandplan Offline-first LLM knowledge base + planner.

Bricks

Roll a die, flip a coin

Roll or flip

Let's build something.

I'm open to research collaborations, engineering roles, and interesting problems. The best way to reach me is email.

Get in touch