AI engineer and backend builder across production AI systems, cloud-native APIs, RAG applications, agentic workflows, and real-time tools. I care about reliability, latency, cost, and maintainable systems that actually ship.
Highlighted Work
Production-Grade Real-Time Voice Assistant
Real-time voice assistant with adaptive jitter buffering, spectral analysis, and AGC-normalized audio capture for sub-second conversational latency. Features 24 integrated tools (GitHub, utilities, memory), a 6-state orchestrator, Whisper STT, and local TTS via edge-tts. Full audio health diagnostics panel with FFT spectral analyzer.
RAG-Powered Legacy Code Navigator
Semantic search system enabling natural language queries against 150K+ lines of legacy Fortran using vector similarity and LLM analysis. 8 analysis modes — explain, dependency mapping, impact analysis, documentation generation, bug search, and more. Syntax-aware Fortran chunking with ChromaDB, Voyage-code-3 embeddings, and Gemini 2.5 Flash via OpenRouter. Interactive dependency graphs with vis-network. Sub-3s answer generation at ~$0.001/query.
Privacy-First AI Engagement Analytics
Real-time engagement analytics for live tutoring using in-browser MediaPipe Face Mesh (468 landmarks), 52 facial blendshapes, and speech pattern detection. Delivers live coaching nudges to tutors and shareable progress reports. All video/audio processing happens in-browser — zero data leaves the device. WebRTC-powered with AI-generated session summaries.
AI-Powered Wealth Management Agent
Built an AI agent layer on top of an open-source wealth management platform with natural-language portfolio insights. 25 specialized tools covering portfolio analysis, performance metrics, market data, and compliance checks. Multi-layer hallucination verification system with LLM output validation. NestJS + Angular full-stack with PostgreSQL, Prisma ORM, Redis caching, and LangSmith tracing. Pre-seeded with 200+ test transactions.
Kubernetes Diagnostics with 3D Topology
Upload Kubernetes support bundles and get structured root-cause analysis with remediation guidance. 26 heuristic detectors for common K8s failure modes, RAG pipeline with ChromaDB for semantic search across bundles, 3D cluster topology visualization (Three.js), log correlation, and auto-generated preflight checks.
Buildability Assessment for SoCal Parcels
Enter any Southern California address and get full ADU buildability analysis in under 5 seconds. 9-step async pipeline with deterministic zoning rule engine, Shapely geometry for buildable envelope computation, Mapbox GL 3D visualization, LLM-powered explanations, and PDF export. Multi-jurisdiction design supporting CP-7150 and LAMC regulations.
About Me
I build production AI systems and backend platforms across RAG applications, agentic workflows, real-time AI tools, REST APIs, ML pipelines, and cloud-native services.
3+ years across ST6 Partners, Gauntlet AI, ZenZiee, Buildoors Lab, and Infosys, with hands-on work in Python, Java, TypeScript, AWS, FastAPI, Spring Boot, PostgreSQL, Docker, Kubernetes, and event-driven systems. MS Computer Science from Arizona State University (3.8 GPA).
Skills
Tech Stack
- Languages
-
PYTHON
-
JAVA
-
TYPESCRIPT
-
GO
-
C++
- Backend & APIs
-
FASTAPI
-
SPRING BOOT
-
NODE.JS
-
NESTJS
-
FLASK
- Cloud & Data
-
AWS
-
POSTGRESQL
-
MONGODB
-
REDIS
-
DOCKER
-
KUBERNETES
- AI / ML
-
RAG + AGENTS
-
PYTORCH
-
TENSORFLOW
-
KAFKA
-
LLM APIS
- Tools
-
GIT
-
GITHUB
Education
Master of Science in Computer Science
Jan 2024 – Dec 2025 | Tempe, AZ, USA
• GPA: 3.8/4.0
• Coursework: Statistical ML, Algorithms, Cloud Computing, NLP, Data Mining, Networks
• Focus on AI/ML and scalable cloud architectures
B.E. in Computer Science and Engineering
Jun 2016 – May 2020 | Solapur, India
• GPA: 9.23/10
• Coursework: Data Structures, Operating Systems, Big Data, Web Development
• Strong foundation in computer science fundamentals
Experience
• Building production AI systems and backend workflows with Python, TypeScript, APIs, and cloud deployment
• Applying AI-assisted engineering practices to ship reliable backend services, automation, and model-powered product workflows
• Focused on maintainable systems with strong attention to reliability, latency, cost, and deployment quality
• Built Jarvis, a production-grade voice assistant with adaptive jitter buffering, 24 integrated tools, and sub-second latency
• Shipped 12+ production AI applications across RAG, agentic workflows, real-time voice, and AI orchestration with live deployments
• Built LegacyLens, a RAG system for semantic search over 150K+ lines of legacy Fortran using ChromaDB, Voyage embeddings, and Gemini 2.5 Flash
• Built GhostGuide, an AI portfolio-analysis agent layer with 25 tools, hallucination checks, and a NestJS, Angular, PostgreSQL, and Redis backend
• Built ZenZiee, a gamified social app with real-time APIs, analytics dashboards, and user sentiment tracking for 100+ beta users
• Deployed containerized microservices using AWS ECS/ECR, ALB, CloudWatch, achieving 99.9% uptime
• Designed event-driven pipelines with DynamoDB Streams, Lambda, S3, reducing processing latency by 60%; collaborated with ML/frontend teams to embed emotion classification, increasing engagement by 25%
• Developed blockchain-based fraud detection system, reducing risk exposure by 35%
• Automated ETL pipelines and built compliance dashboards using Pandas, SQL, Tableau, Power BI
• Deployed ML models on AWS SageMaker with automated retraining and monitoring workflows
• Designed Java Spring Boot microservices and REST APIs for enterprise billing systems, reducing manual effort by 50%
• Improved backend performance by 35% through MSSQL query optimization
• Managed 1M+ EDI transactions per month using IBM Sterling; implemented CI/CD pipelines reducing release cycles by 45%
All Projects
Gamified AI Scenario Training for Options Traders
Autonomous AI Ad Copy Pipeline
Real-Time Collaborative Whiteboard with AI
AI Writing Assistant & Content Platform
AI WordPress Block Theme Generator
K-12 AI Tutoring with App Orchestration
AI Fraction Tutor for Ages 5-8
AI-Powered E-Commerce Onboarding Assistant
Multilingual AI Education Assistant
District Literacy Leader Matching Platform
Event-Driven Analytics Platform
Fine-Tuning LLaMA for Reasoning
Real-Time Graph Analytics Pipeline
AI Reading Comprehension Assistant
Cloud-Based Face Recognition System
Store Sales Time-Series Forecasting
ML-Based News Classification
Logic-Based Layout Optimization
FABRIC Testbed Network Measurements
Contact
Or reach me directly at ykucheri@asu.edu