AI Researcher & Engineer · UC San Diego

PranavSoma.

I build AI and I ship it.

I'm finishing my M.S. in Computer Science at UCSD with a 4.00 GPA. Right now I lead an agentic AI platform used by 7,000+ people on campus, train multimodal health models on a supercomputer, and last summer I shipped voice agents to production at ServiceNow and tested them live with Disney+. I'm looking for research and AI engineering roles, ideally in the Bay Area.

See my work Résumé Email me
Pranav Soma
Open to roles
in the SF Bay Area
0
GPA in my CS master's
0
students using my AI tutor
0
latency I cut at ServiceNow
0
raised by a platform I led
0
students in a group I co-founded
PythonPyTorchLLM fine-tuningLoRARLHFGraphRAGMCP serversReactFastAPIAWSXGBoostOpenCVDockerMongoDBC++TypeScriptNodeFlaskpymetisTransformers PythonPyTorchLLM fine-tuningLoRARLHFGraphRAGMCP serversReactFastAPIAWSXGBoostOpenCVDockerMongoDBC++TypeScriptNodeFlaskpymetisTransformers

A demo is a guess. Production is the proof.

Most of what I've built is running for real users right now, not sitting on a slide.

Experience

Where I've worked

The places I've owned real work, from a live enterprise launch to research that runs for thousands of people.

2025
Live with Disney+

Software Engineer Intern @ ServiceNow

I took the AI Voice Agents platform off a version of AWS Lex that was about to be killed, moved it to the new one ahead of schedule, and got it into production. We tested it live with Disney+ before my internship was even over. I also rebuilt the language-understanding pipeline across 8 intents and cut response latency by 75%. They gave me a return offer, and I won the Technical Skills Award at UCSD's symposium (out of 800+ interns).

AWS LexLambdaJavaScriptPythonPostgreSQL
2025 - now
Teradata-funded

AI Research Fellow & Agentic Systems Lead @ Lab for Emerging Intelligence

I lead an agentic AI platform that 7,000+ students, faculty, and staff at UCSD use. That means custom MCP servers over the university's APIs and a workflow engine I built to stay reliable when things go wrong. I also built and shipped an AI tutor that's now running for 8,000 students across UCSD, SDSU, and Cal Poly Pomona. We A/B tested it: TA hours dropped 64% and engagement went up 87%.

MCP serversLoRA / SFT / RLHFFastAPIMongoDB
2024 - 2025
Health AI

Graduate Researcher @ Qualcomm Institute (HXI Lab)

I work on LifeSaver, an assistant that reads sensor, audio, and video data and turns it into something a health database can answer, built for emergency services, the elderly, and rural care. I trained multimodal models on the San Diego Supercomputer Center and used GraphRAG over the UMLS medical ontology to keep answers accurate and fast enough for emergencies. I'm first author on the lab's poster.

Multimodal LLMsQwenGraphRAGUMLS
2024
Intern lead

Software Engineer Intern @ Work4Flow

I led a team of 6 interns. We shipped GenAI Observer, a tool that scores the prompts engineers write and tells them how to make them better, plus an integration connecting ServiceNow and Smartsheet with some LLM categorization. Both got the green light from the PM to go to customers.

LLM evalServiceNowSmartsheet
Research

What I'm researching

Three projects where the methods are hard and the output has to work for real people.

01

LifeSaver: multimodal AI for emergency and rural care

Qualcomm Institute / Calit2 · HXI Lab

An assistant that turns messy real-world signals (sensors, audio, video) into structured answers a clinician or first responder can use. I trained the models on a supercomputer and grounded them with GraphRAG over a medical ontology so the answers are both right and fast enough to matter in an emergency. I also wired up the robotics side that drives the actual hardware.

Multimodal LLMsQwen SFTGraphRAGUMLSSupercomputer
02

Computational redistricting: fairness in congressional maps

★ Applying to ACM CHI 2026 · presenting at the SF Exploratorium, Dec 2026 · UCSD CSE honors thesis

My honors thesis. It draws and scores U.S. congressional maps over Census data, anywhere from 158K to 5.5 million blocks per state. I built three different map generators (a greedy heuristic, a Monte Carlo sampler, and an XGBoost model with graph partitioning) and wrote the fairness metrics that grade them, things like the efficiency gap and Voting Rights Act compliance. It reproduces the real district counts for Alabama, California, and Texas.

XGBoostpymetisMonte CarloGeoPandasCensus data
03

Agentic systems and a deployed AI tutor

Lab for Emerging Intelligence · Teradata-funded

The agentic platform behind the work at LEI: MCP servers over the university's APIs and a workflow engine built to degrade gracefully when something breaks, because 7,000+ people feel it when it does. The AI tutor that came out of it runs for 8,000 students and cut TA hours by 64% in an A/B test, using LoRA/SFT/RLHF fine-tuning and Bayesian knowledge tracing.

MCP serversWorkflow engineLoRA / SFT / RLHFFastAPI

I'll take the harder problem if it's the one that actually helps someone.

The elderly, an ER, students without enough TAs. I keep ending up there on purpose.

Projects

Stuff I've built

Side projects and competition work, taken from idea to something that actually runs.

ORCA, an AI music production project

ORCA Best Project

SDTC, picked 1 of 30 from 200+ · SAIRS 2025

An AI music tool that reads sheet music into audio and turns audio back into a score. OpenCV reads the page, neural nets split out the instruments, and a CNN writes the score. It hit 98% accuracy, which I checked four different ways including having actual musicians grade it.

OpenCVCNNFlaskDockerReact

Spay.LA

Engineering manager, team of 11

A fundraising and advocacy platform I led for a real client. It raised $75K. I ran the team and owned everything from scoping with the client to shipping.

spay.la →

BioVeritas

AI for scientific rigor

A tool that checks how sound and honest a piece of biology research is, using retrieval to back up what it flags.

Union Station Housing

Software developer

A listing platform for the main housing provider in greater LA. Photo and video upload, form validation, and bulk data exports for their team.

Skin Lesion Detector

E/Acc research group

An image classifier for spotting skin lesions, built to run on small on-device hardware.

Virtual Trial Room

E/Acc research group

A 3D fitting room using deep learning and computer vision so you can see how clothes look without trying them on.

Leadership

What I've started

I tend to start things. These are the communities I've built and helped run.

Real World AI Network

Co-founder & president

I co-founded a 7,000+ student group that spans UCSD's engineering, data science, and business schools. It exists to push AI research, building, and startups across the whole university.

University AI Alliance Nation's largest

Founding board, VP of external affairs

I helped start the biggest student-led AI initiative in the country, with people from MIT, Stanford, Caltech, and Cornell. I run the outside relationships: VCs like a16z speedrun and Techstars, and folks from Google and Meta.

CSE Society @ UCSD

President

I lead UCSD's oldest computing org, 100+ members. We run career fairs, conferences, talks, and a research journal, and we partner with the Linux Foundation and Cisco on open source.

E/Acc Research Group

Founder

I started a research group that brings AI into other fields, working with UCLA, UCSB, and UCSC. I ran 30+ people across ORCA and a couple of other projects.

Next, I want to do this where the models are biggest and the stakes are real.

Research and AI engineering at the labs pushing the frontier. And I'll keep building the Real World AI Network into something that outlasts me.

Recognition

Some things I'm proud of

2025
ServiceNow Technical Skills Award TOP INTERN
Top intern out of 800+ at UCSD's Summer Internship Symposium.
2026
YC Startup School 2026 YC
Picked for Y Combinator's Startup School.
2025
Best Project, SDTC
ORCA, chosen as 1 of 30 out of 200+ applications. Also shown at SAIRS 2025.
2025
Cum Laude & CSE Department Honors
UC San Diego, B.S. Computer Science. Provost Honors every quarter.
·
National Merit Finalist
Also AP Scholar with Distinction and a National Speech & Debate award.
·
USACO Silver
USA Computing Olympiad.
About

I grew up building robots and somewhere along the way got obsessed with putting AI in front of real people.

I'm from Cupertino, and I run pretty wide: systems, ML, theory, full-stack, robotics. The thing I keep coming back to is taking something that only works in a notebook and getting it to run for someone who actually needs it, whether that's a student without enough TAs, an ER, or a family in a town with no doctor nearby.

I care about the work being real. A demo is a guess. Production is the proof. That mindset came from years of competition, robotics, debate, and a USACO Silver, and it's why I'd rather pick the harder, more useful problem.

Next, I want to do this where the models and the stakes are biggest. I'm aiming for research and AI engineering roles at the labs pushing things forward, and I'll keep building the Real World AI Network into something lasting along the way.

Contact

Let's talk.

prsoma@ucsd.edu
Résumé LinkedIn GitHub

Targeted résumés: Software, Machine Learning, Forward Deployed

Based in San Diego, open to relocating anywhere in the SF Bay Area.