Sidhartha Vyas
Open to work1 years experienceBackend Engineer
Backend & GenAI Engineer | LLM Application Developer
Standing Rank
Rank Not Available
Developer Badges
No badges earned yet
Skills & Technologies
39 skillsWork Experience
Backend Software Developer
Datrax Services Pvt. Ltd.
- Architected MPNC, a production backend platform for real-time inventory lifecycle management, batch tracking, expiry automation, and demand forecasting across multi-location KFC restaurant operations.
- Designed and deployed 20+ REST APIs using FastAPI and Python — FIFO ledger logic, automated state-transition engines, and procurement forecasting modules.
- Engineered SQL Server query optimisation pipelines — stored procedures, indexing, and reporting modules — powering operational analytics for franchise management.
Software Engineer Intern — Backend
Translogistics Pvt. Ltd.
- Built secure, high-throughput REST APIs in Node.js for a logistics CRM, enabling real-time data management and third-party service integrations.
- Optimised PostgreSQL schemas, indexes, and query execution plans, reducing query latency and improving data throughput across logistics workflows.
Software Engineer Intern — IoT & Backend Systems
Vighnesh.inc
- Built IoT data ingestion handlers improving processing accuracy by 30% through enhanced validation and fault-tolerant error-handling logic.
- Refactored real-time encoder feedback pipelines using event-driven architecture, achieving a 40% reduction in processing latency.
Projects
DocuMind AI — Production RAG Document Assistant
- Architected a full end-to-end RAG pipeline: PDF ingestion with dual-extractor fallback (pypdf + pdfplumber), recursive text chunking (512 tokens / 50 overlap), local embedding generation via Sentence Transformers (all-MiniLM-L6-v2, 384-dim), and persistent vector indexing in ChromaDB.
- Built a lightweight Intent Classifier using cosine similarity over embeddings (6 intents: summarization, comparison, definition, troubleshooting, factual, greeting) with intent-aware retrieval multipliers and CrossEncoder reranking (ms-marco-MiniLM-L-6-v2) for two-stage candidate narrowing.
- Engineered a multi-provider LLM orchestrator (Gemini, OpenAI, Groq, OpenRouter) with tenacity-based retry logic; integrated RAGAS evaluation (faithfulness, answer relevance, context precision/recall) on 5% sampled queries for continuous quality monitoring.
- Delivered a React 19 + Vite dashboard with real-time intent badging, citation source inspector, RAGAS playground, and live ChromaDB metrics; backend exposed via 9 FastAPI endpoints with full OpenAPI docs.
CyberGuard — AI-Powered Real-Time Content Moderation Platform
- Fine-tuned MuRIL and Toxic-BERT transformers for multilingual toxicity classification; built a Gemini API fallback layer creating a hybrid AI inference pipeline for Twitter and Discord moderation.
- Engineered FastAPI AI inference microservices with Redis Pub/Sub & WebSockets for real-time moderation; built a synthetic dataset generation pipeline to augment training data.
AI Interview Platform — Gemini-Powered Mock Interview System
- Built an AI mock interview system using Gemini API with multi-turn prompt engineering for dynamic question generation, conversational evaluation, and structured JSON feedback via FastAPI LLM orchestration.
Leaderboard Standings
Leaderboard Position Pending
Global test scores, peer standing percentiles, and algorithm leaderboard ranks are updated dynamically.
Assessment Highlights
Assessments Not Completed
Coding evaluations, system assessment results, and conceptual score badges will appear here after taking a test.
AI Collaboration Score
AI Collaboration Score Pending
Developer coding behavior, assistant cooperation, and AI pair-programming indicators are evaluated during live coding sessions.
Role Compatibility Profile
Role Compatibility Analysis Pending
Custom matching reports, candidate role compatibility percentiles, and core engineer strength profiles are processed once conceptual code screenings are complete.
Achievements
Achievements Not Earned
Special rewards, developer badges, system recognition certificates, and conceptual milestones will display here.
About Details
Professional Bio
Backend & GenAI Engineer with 1.5+ years of production experience building scalable REST APIs, AI inference microservices, and LLM-powered applications. Proficient in Python, FastAPI, Node.js, PostgreSQL, SQL Server, and Redis.
B.E. Electronics & Computer Science
Thakur College of Engineering & Technology (TCET) ( - 2026)