Standing Rank
Rank Not Available
Developer Badges
Badges Pending
Skills & Technologies
31 skillsWork Experience
Work Experience Not Populated
Professional job history, career timeline, and previous industry roles will show here once linked or added.
Projects
Cortex | Multi-Tenant RAG Platform
- Production platform with 170 visitors, 417 page views in last 30 days (+448% growth) — multi-tenant with Google OAuth, Supabase row-level security, and route-level RBAC
- Implemented hybrid RAG pipeline — semantic chunking, pgvector dense search + PostgreSQL BM25 sparse search fused via Reciprocal Rank Fusion (RRF) for highest-quality retrieval
- Built custom SSE streaming layer delivering LLM tokens to UI at zero latency — no blocking wait for full response, dramatically improving perceived performance
Column8 | Agentic AI Platform — Voice Interview + ATS Scoring
- Production SaaS with real paying users — 141 visitors, 339 page views in last 30 days (+176% growth), Razorpay monetized with HMAC webhook verification and credit-based access gating
- Built live voice interview simulator over WebRTC — AI hiring manager loads candidate resume and JD as live context, conducts real-time adaptive interview with STT/TTS pipeline
- Designed two-stage agentic ATS scoring pipeline using Zod schema-enforced structured outputs — LLM performs semantic matching against JD requirements, bypassing hallucination-prone free-form generation
- Implemented SSE streaming for zero-latency token delivery to UI — integrated Upstash Redis sliding- window rate limiting replacing unbounded in-memory Map causing RAM leaks in production
Nexus | Real-Time WebRTC Voice AI Agent
- Built end-to-end real-time voice agent — LiveKit WebRTC orchestrating Deepgram STT, Groq LLM inference (Llama 3.3 70B), and Deepgram TTS as three coordinated async FastAPI services
- Achieved sub-second conversational latency on Indian cellular networks — engineered HTTP timeout detection with live model failover to backup LLM endpoints under API failures
- Implemented native ChromaDB RAG pipeline firing mid-conversation as an LLM tool call — retrieved context surfaces in real time without blocking voice response stream
- Containerized all services with Docker multi-stage builds and docker-compose — single command deployment, production-ready
Kavya | Bilingual Voice AI Collections Agent
- Built production-grade outbound voice AI agent for NBFC loan collections — bilingual state machine (Hindi/Hinglish/English) with automatic language detection and mid-call switching
- 8-branch conversation state machine: happy path, already paid, financial hardship, loan dispute, DND request, angry customer, wrong number, voicemail — RBI Fair Practices Code and TRAI compliant
- Implemented post-call structured JSON output for CRM integration — call_outcome, promise_date, sentiment, language_used, escalation_reason
Clary | Agentic Clinical Reasoning Engine
- Architected two-stage agentic reasoning pipeline — Stage 1 extracts structured data, Stage 2 performs causal reasoning, with strict Pydantic schema enforcement physically rejecting malformed LLM outputs
- Engineered model-fallback circuit breakers with dynamic LLM routing — auto-switches on rate limits or failures, ensuring 99.9% pipeline uptime
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
AI Engineer with hands-on production experience building real-time voice AI systems, agentic LLM workflows, and low-latency backend pipelines. Shipped 5 production systems independently, including WebRTC voice agents and multi-tenant RAG platforms.
B.Sc. Computer Science & Electronics in Computer Science & Electronics
P. C. Jabin Science College, KLE Society's (2022 - 2025)