Abhinav Srivatsa

> Building

01_Experience

Lira Lab (USC)

Grad. Student Researcher
PyTorch • Vision Transformers (ViViT) • Imitation Learning

Extending the GABRIL framework (Gaze-Based Regularization) to web agents by engineering a custom Video Vision Transformer (ViViT). Currently training on high-dimensional Atari datasets to prove that gaze-augmented attention mechanisms improve sample efficiency in complex tasks.

BlackRock

SWE Intern (Risk & Quant.)
Python • SQL • Quantitative Analysis • Git

Engineered Python pipelines for critical portfolio risk metric calculations. Optimized complex SQL queries on 4M+ record datasets, reducing execution latency by 15% for daily executive reporting. Modernized legacy infrastructure by migrating embedded queries to a version-controlled Git workflow.

Emotorad

Cloud & Backend Eng. Intern
Go • Kafka • Flink • Kubernetes • Cassandra • MQTT

Architected a real-time IoT ingestion pipeline for 10,000+ e-bikes (80GB/day). Replaced WebSockets with MQTT and Kafka to handle high-concurrency streams. Implemented stateful processing with Apache Flink and reduced bandwidth usage by 60% using Protocol Buffers.

02_Projects

Ctrl-F: Intelligent Video Search (TreeHacks 2026)

NVIDIA DeepStream • Jetson Orin • Elasticsearch • RAG

Built an edge-to-cloud surveillance system in a 36-hour TreeHacks sprint, deploying a real-time YOLO pipeline on NVIDIA Jetson and enriching frames with local VLMs (NanoLLM). Indexed observations into a serverless RAG backend on Modal with Elasticsearch vectors to support ranked, natural-language video search.

Catan Infrastructure

Docker • Cloudflare • Mongo • Go

Orchestrated a secure, self-hosted multiplayer platform. Integrated custom game assets into a modified open-source frontend, resolving dependency conflicts to ensure a seamless UI experience. Secured public access via Cloudflare Zero Trust tunnels (no open ports).

Chess Bot

RE-ENGINEERING
PyTorch • MCTS • Deep Reinforcement Learning

Reproduced the AlphaZero architecture from scratch. Engineered a dual-headed Convolutional Neural Network (CNN) in PyTorch to predict policy and value, integrated with Monte Carlo Tree Search (MCTS) for lookahead.

Wynter's Dreams

Go • AWS ECS + Lightsail • PostgreSQL • CI/CD

Architected a cloud-native content platform using Go and PostgreSQL. Orchestrated containerized microservices on AWS ECS and managed the full CI/CD lifecycle to support production traffic for 50+ active users.

03_Published_Research

LSTM-Based Market "Hype Detector"

TensorFlow (LSTM) • Go (Colly) • yfinance • Python

Engineered a polyglot data pipeline to predict stock volatility. Built a high-concurrency web scraper in Go (Colly) to harvest news sentiment, fused with market data via yfinance, and trained a TensorFlow LSTM model to detect market hype trends.

04_Library

user@adsrivatsa:~ cat /library/reading_list.txt Total_Entries: 42
[SCI-FI] The Three-Body Problem // Cixin Liu
[FANTASY] The Name of the Wind // Patrick Rothfuss
[SCI-FI] Project Hail Mary // Andy Weir
[CLASSIC] 1984 // George Orwell
[FICTION] The Midnight Library // Matt Haig
[LOADING...] Designing Data-Intensive Applications // Kleppmann