Soumya Patel — Software Engineer & AI Developer

SoumyaPatel

Syllabus parsing requires extracting highly structured timelines from messy PDFs without blowing up API token costs, while handling real-time voice inputs on the frontend and keeping strict academic integrity safeguards.

Built a Next.js frontend with Tailwind CSS and Framer Motion, integrated with a FastAPI Python backend. Used the browser's Web Speech API to build a voice onboarding flow, set up AWS Cognito for auth, uploaded documents to S3, and called Gemini AI. Made custom prompt guardrails and a hybrid caching/routing engine to reduce API usage by 70%.

Deployed a functional web app that helps students onboard in seconds using voice commands. Integrated speech recognition APIs, optimized LLM costs, built prompt guardrails, and scaled cloud infrastructure.

Natural language combinatorics questions exhibit highly varied grammar, making traditional rule-based parsers fragile. Conversely, utilizing heavy LLMs introduces unwanted latency, API costs, and overhead for extracting simple algebraic parameters.

Built a Flask backend powered by scikit-learn. Developed a custom NLP pipeline using an SVC to classify the problem type, and combined it with a Regex parser to extract numerical constants and output the corresponding LaTeX math formulas.

Reached 92% classification accuracy to provide instant math solutions. Integrated scikit-learn models with a Flask backend and rendered LaTeX math formulas dynamically on the frontend.

Manual client mod management is error-prone and version-dependent, while unoptimized Java settings cause periodic in-game lag spikes (garbage collection stutter).

Built a desktop client using Electron and Node.js that communicates with the Modrinth API to resolve and install Fabric mod JARs directly to the user's local directory via Node's fs and https modules. Validates ZIP headers and EOCD signatures at the binary level to detect and auto-repair corrupted downloads. Automatically applies low-latency GC flags (UseG1GC) and caps frame rates to eliminate micro-stuttering. Integrated minecraft-launcher-core to handle authenticated game startup, and set up Electron IPC channels via a preload script to stream real-time launch status back to the renderer UI.

Automated local game environment setup. Managed third-party APIs (Fabric/Modrinth), handled file downloads, persisted local configurations, preventing corruption crashes and tune JVM garbage collectionand worked with Electron's main/renderer IPC bridge.

Unmanaged database connections lead to connection pool leaks, unparameterized strings create SQL injection attack vectors, and unhandled transaction failures cause inconsistent database state.

Architected an abstracted connection layer utilizing Python context managers (__enter__ and __exit__) for deterministic resource cleanup. Implemented strictly parameterized SQL execution pipelines to ensure query sanitization, and automated transaction rollbacks upon execution failure.

Designed 3NF normalized schemas, managed transactional safety (commit/rollback lifecycles), and isolated business logic from raw database drivers.

Keeping the bot responsive under rapid chat activity while running database queries, auto-mod checks, and translation API calls without locking the main Python thread.

Organized features into modular cogs using discord.py and aiosqlite. Used non-blocking database queries to prevent freezing, in-memory sliding window checks for spam rate limits, and asynchronous HTTP calls for translation.

Writing asynchronous Python code with AsyncIO, managing non-blocking SQLite database operations, and structuring maintainable event-driven bots.

When speakers talk fast or have heavy accents, it is easy to miss key points in large lecture halls—especially when distant audio is too quiet for standard speech recognizers.

Pulled live mic streams using PyAudio in a background thread, added volume gain so quiet voices get boosted automatically without clipping, and fed audio chunks to a quantized faster-whisper model. Added a post-session Gemini script to format raw text into clean bullet points.

Handled live mic audio in Python without blocking the terminal, adjusted gain levels to filter out ambient room noise, and ran local Whisper models smoothly without needing a dedicated GPU.