[NODE_CONNECT: ESTABLISHED]
SYSTEMS_ARCHITECT // READY_FOR_DEPLOYMENT
_
Core Focus
Deploying scalable AI infrastructure and RAG ecosystems for enterprise intelligence.
Current Status
4th Year Student / AI Developer Intern @ Mendygo
System Telemetry
> LLM_INFERENCE: STABLE
> VECTOR_DB: OPTIMIZED
> MLOPS_CI_CD: ACTIVE
> VECTOR_DB: OPTIMIZED
> MLOPS_CI_CD: ACTIVE
System Architectures
Production case studies & deployments
Work Experience
Professional trajectory & impact
Status: Employed // Active
Sep 2025 – May 2026
Mendygo
Remote
AI Engineer Intern
Enterprise Document Intelligence
Worked on building enterprise-oriented AI systems focused on Retrieval-Augmented Generation (RAG), document intelligence, and contextual knowledge retrieval. Designed pipelines allowing LLMs to access external knowledge sources efficiently while maintaining accuracy, scalability, and low operational costs.
RAG & Document Intelligence
- Designed RAG architectures reducing hallucinations
- Built ingestion pipelines (PDF, DOCX, TXT)
- Implemented text extraction, chunking, and indexing
Semantic Search & LLMs
- Built FAISS-based vector retrieval pipelines
- Integrated local Ollama models for privacy
- Applied prompt engineering for context relevance
Azure & API Development
- Deployed scalable AI services on Azure
- Built FastAPI REST endpoints for integrations
- Managed cloud infrastructure and CI/CD pipelines
Engineering Decisions
- Chose RAG over Fine-Tuning for dynamic updates
- Prioritized low inference costs and rapid deployment
- Ensured high knowledge freshness in enterprise KBs
LangChainFAISSOllamaPythonFastAPIAzureDockerGitLab CI/CD
"Gained hands-on experience working across the entire AI lifecycle: Data → Retrieval → LLM → API → Deployment → Monitoring, moving beyond experimentation to scalable production-ready solutions."
LET'S
TALK_
Looking to deploy scalable AI infrastructure or need a robust RAG ecosystem? Let's connect and build something impactful.