# Rohan Kumar

> Software Engineer at Eudia | Full-Stack AI Systems & LLM Inference | UCSB Alum

Location: San Jose, California, United States
Profile: https://flows.cv/rohankumar

I build production AI systems: the pipelines, feedback loops, and evaluation infrastructure that make LLMs reliable and improvable in the real world.  

Currently at Eudia, where I work full-stack across the entire AI delivery chain: document ingestion and parsing, LLM inference pipelines, human-in-the-loop review tooling, and eval loops that surface structured improvements back into the model. I've shipped systems like this across four regulated industries including government contract review, pharma regulatory compliance, and consumer review moderation. 

Before Eudia, I interned at LiveRamp (data infrastructure and CI/CD), Grafiniti (LLM reasoning pipelines for FinTech), and AIClub (real-time computer vision on iOS).  

My background is CS + Physics (quantum mechanics focus) from UCSB, which shapes how I think about systems: mathematically rigorous, not just empirically.  Open to roles in AI/ML engineering, LLM infrastructure, or applied research engineering where strong systems thinking meets production AI.

## Work Experience
### Software Engineer @ Eudia
Jan 2025 – Present | Palo Alto, CA
- Designed and own the full-stack AI feedback loop: reviewers annotate model errors in a React/TypeScript UI I built; corrections flow through a Python/FastAPI pipeline into an eval system that restructures prompts and playbooks — improving recall from 55% to 92% after 15 annotated documents for a major enterprise customer
- Sole frontend engineer on the compliance product; own 100% of frontend code across the core product and multiple pilot applications built to close enterprise deals
- Reduced pipeline latency 3× (8 min → 3 min) by replacing LLM inference with Python post-processing where the model was being used for deterministic logic, then parallelizing the remaining independent stages
- Designed fault-tolerant Temporal workflows with idempotent retries, task queues, and parallel fan-out for correctness under bursty enterprise workloads
- Shipped a 0→1 production system on a 3-engineer team in 6 weeks; deployed full-stack pilot applications solo across government ACR contract review, pharma regulatory compliance, environmental marketing compliance, and pharma consumer review moderation

### Software Engineer @ LiveRamp
Jan 2024 – Jan 2024 | San Francisco, CA
- Built a dry-run safety layer in Rails/PostgreSQL for high-risk administrative operations, enabling preview of database mutations before execution in production
- Built automated smoke-testing services to proactively detect production failures pre-release, reducing on-call incidents
- Improved CI/CD reliability with automated visual regression testing, reducing UI-related review cycles

### AI Engineer @ Grafiniti
Jan 2023 – Jan 2023 | San Jose, CA
- Designed multi-step LLM reasoning pipelines using LangChain for FinTech workflows, reducing financial brief generation time by 60×
- Developed dynamic system prompts refined iteratively with domain experts, improving output accuracy and consistency
- Built bulk review and evaluation tooling to support human-in-the-loop validation and accelerate prompt iteration cycles

### AI Engineer @ AIClub
Jan 2022 – Jan 2022 | San Jose, CA
- Built real-time computer vision pipelines (TensorFlow, Swift) integrated into a production iOS application for AI education
- Authored and deployed the majority of AIClub's computer vision curriculum, adopted by hundreds of students


## Education
### Bachelor of Science - BS in Computer Science
UC Santa Barbara

### High School Diploma
Archbishop Mitty High School


## Contact & Social
- LinkedIn: https://linkedin.com/in/kumar-roh

---
Source: https://flows.cv/rohankumar
JSON Resume: https://flows.cv/rohankumar/resume.json
Last updated: 2026-04-10