Building production-oriented AI systems with a focus on scalable LLM applications, backend engineering, and retrieval-based architectures.
AI/ML Engineer focused on designing and building production-grade AI systems.
My work centers on integrating machine learning models into backend systems, with emphasis on reliability, scalability, and real-world deployment.
I specialize in LLM-based applications, retrieval-augmented generation systems, and backend architecture for AI-driven products.
- Applied AI Systems (LLM applications, RAG pipelines, prompt orchestration)
- Backend Engineering (REST APIs, system design, service integration)
- Retrieval Systems (semantic search, embeddings, document QA)
- AI Workflows (automation pipelines, structured reasoning systems)
- Model Integration (ML models in production environments)
Languages: Python, C/C++
Backend: FastAPI, Flask, REST APIs
Databases: PostgreSQL, MySQL
Machine Learning & Deep Learning: PyTorch, TensorFlow, Scikit-learn
LLM & Retrieval: Hugging Face, LangChain, LangGraph, FAISS
Tools: Docker, Git, MLflow
Agritech Systems
- Field data pipelines and operational systems
- Geospatial data processing
- Weather-based advisory logic
- AI-assisted decision support systems
AI Workflow Systems
- Retrieval-based AI assistants
- Multi-step reasoning pipelines
- Document processing systems
- API-driven automation workflows
Knowledge Systems
- Vector search implementations
- Context-aware QA systems
- Retrieval-augmented architectures
- Structured knowledge pipelines
- Build systems that are simple and maintainable
- Treat AI as a component within larger systems
- Prioritize production reliability over experimentation
- Focus on backend-first AI architecture
- Continuously iterate through real-world implementation
B.Sc. in Software Engineering (Data Science Focus)
Daffodil International University (2022 – 2026)
- Production LLM systems
- Scalable RAG architectures
- AI backend infrastructure
- Retrieval-based systems design
- Real-world AI deployment