Professional Overview
AI Engineer & Full-Stack Dev specialized in production GenAI. I build scalable RAG platforms using LLMs, LangGraph, FastAPI, and Next.js. Proven track record of reducing hallucinations and improving speed from minutes to seconds. I bridge the gap between complex data systems and business impact, reducing manual effort by up to 80%.
Experience
AI Expertise
Skills
Description of Responsibilities
- Built AI test platform using Next.js, FastAPI, RAG, and OpenShift for 100+ users
- Reduced test gen time from 20m to 2m and grew coverage to 90% via async flows.
- Cut LLM token use by 75% via prompt decomposition and JSON schema validation.
- Developed RAG pipelines for diverse files, boosting AI output quality by 90%.
- Engineered async Jira ingestion layer to sync 2M records via aiohttp/asyncio.
Key Achievements / KPIs
- Built multi-provider LLM orchestration across Gemini, Claude, and Vertex AI.
- Designed 51-table Postgres schema with pgvector and GIN indexing for performance
- Compressed ETL phases from 15m to 20s using MD5-based CDC and async SQLAlchemy.
AI Expertise
Skills
Description of Responsibilities
- Built full-stack event platform with modern frontend and backend API patterns.
- Designed database entities and responsive UI to scale content management.
- Developed role-aware access and validation to improve registration reliability.
- Streamlined administrative workflows to reduce manual program coordination.
- Engineered structured data flows for better visibility across events and program
AI Expertise
Skills
Description of Responsibilities
- Enhanced enterprise CRM apps and insurance forms for finance and energy clients.
- Built workflow modules and backend integrations to boost user productivity.
- Collaborated with stakeholders in Agile cycles to deliver technical designs.
- Developed reusable components and defect fixes for production-ready releases.
- Managed database queries and API integrations to ensure application stability.
Key Achievements / KPIs
- Conducted production issue analysis and maintained detailed release docs.
- Automated data validation and reporting using TOSCA and SQL-driven logic.
- Strengthened data quality foundations to support downstream AI and analytics.
Education
Field of Study: Information Technology and Management
Areas of Expertise
AI & Machine Learning Engineers
Design, train, and ship production ML models — from data pipelines to model inference at scale. Covers supervised learning, neural networks, LLM integration, and model optimisation.
Automation & AI Workflows
Build intelligent automation pipelines, integrate AI APIs into existing tools, and replace manual workflows with agentic AI systems.
AI Product & Strategy
Translate AI capabilities into product roadmaps, define success metrics, and drive adoption across engineering and business teams.
