Aryan Sahni · CS, UC Santa Cruz · Cum Laude
BuildingAIsystemsthatthink,speak,andremember.
Engineering real-time voice AI and agentic systems. Founding Engineer at Aura, incubated at South Park Commons. Previously Snowflake.
Selected projects · 2024 — 2026
Things I've built.
Voice-first AI companion app with cycle-phase awareness and persistent semantic memory. Architected the full real-time pipeline: Groq Whisper STT → LLaMA 3.3 70B → ElevenLabs Flash v2.5 TTS → LiveKit WebRTC, with phase-conditioned memory retrieval using pgvector composite scoring. Built at South Park Commons, SF.
- React Native
- Supabase
- pgvector
- Groq
- ElevenLabs
- LiveKit
- Expo
8-agent ReAct system collapsing 30-minute outreach into 60 seconds. Resume gap analyzer, warm-path finder, and 0–100 response-rate scorer.
- React
- FastAPI
- Groq
- Apollo.io
- Gmail API
Autonomous AI software factory — ideation through deployment on ECS Fargate. Six self-healing maintenance agents replace PagerDuty with semver-aware auto-merge.
- Next.js
- AWS ECS
- Nemotron 120B
- PostgreSQL
Full-stack agent reviewing GitHub PRs in under 60s with line-level inline comments. Resilient inference layer with model failover and self-healing JSON parser.
- Next.js
- FastAPI
- GitHub API
- NVIDIA NIM
Multi-agent stock analysis tool. Enter a ticker and 8 specialized agents — price, news, sentiment, technicals, fundamentals, bull case, bear case — stream live over SSE before a Portfolio Manager agent delivers a BUY/HOLD/SELL verdict with confidence score.
- Python
- Flask
- React
- Claude
- Finnhub
- SSE
- SQLite
Experience
Where I've worked.
Data Science & Gen AI Intern · Aug 2025 — Dec 2025
Snowflake
- — Built a production Snowpark pipeline processing 2,000+ database tables, re-architecting SQL into batched aggregations to collapse multi-hour runtimes.
- — Engineered an automated metadata classification system reaching 91.7% accuracy, reducing manual review from hours to minutes.
- — Partnered with engineers and stakeholders to translate business requirements into production-grade technical solutions.
Currently
Shipping Aura. Somewhere with good coffee.
Avg voice response latency
~800ms
Current LLM
Llama 3.3 70B
Embedding model
text-embedding-3-small
Retrieval architecture
Hybrid RAG · pgvector
Toolkit
What I work with.
Languages
- Python
- TypeScript
- JavaScript
- SQL
- Bash
AI & ML
- LLM integration
- RAG
- pgvector
- Multi-agent orchestration
- Agentic system design
- Groq
- ElevenLabs
- OpenAI API
- Supabase
Data & Infrastructure
- Snowflake
- Snowpark
- Docker
- Vercel
- Render
- AWS ECS Fargate
- GitHub Actions
Frontend & Mobile
- React
- React Native
- Expo
- Next.js
- Tailwind CSS
- Zustand
- TanStack Query
Backend & APIs
- FastAPI
- Flask
- REST APIs
- Server-Sent Events
- GitHub API
- GraphQL
- LiveKit
- WebRTC
- PostgreSQL
Daily Tools
- Claude Code
- Cursor
- GitHub Copilot
Contact
Let's build something worth remembering.
Open to SWE and AI/ML roles. Building agents, voice systems, and the infrastructure between them.