Machine Learning Practitioner & Backend Systems Engineer
I work at the convergence of AI systems, backend engineering, and cloud infrastructure, building practical, scalable solutions that move from idea to deployed product.
My work spans LLM agents and RAG architectures to high-performance APIs that reliably serve ML models in production.
My approach is straightforward: design clean systems, ship iteratively, and scale with intent. Everything I build is rooted in engineering fundamentals and guided by a product-focused mindset.
Deep Learning • LLMOps • RAG Pipelines • Computer Vision
Backend APIs • Cloud-Native Architecture • System Design
Multi-Agent Systems • Model Serving • Vector Search
Languages: Python · C++ · TypeScript
AI & ML: PyTorch · Transformers · Hugging Face · LangChain · LLMOps
LLM Systems: Agents · RAG · Prompt Engineering · Amazon Bedrock
Model Ops: TorchServe · MLflow
Data & CV: Pandas · NumPy · Matplotlib · Keras · Computer Vision · NLP
Backend: FastAPI · Django · Node.js · REST APIs · System Architecture
Databases: PostgreSQL · MongoDB · Redis
Infrastructure & DevOps: Docker · Kubernetes · Terraform · CI/CD · Microservices
Cloud Platforms: AWS · GCP
Vector Databases: Pinecone · FAISS · Weaviate · Milvus
Frontend (Supportive): Next.js · React
I enjoy building systems end-to-end: architecting services, developing ML workflows, and deploying everything through cloud-native pipelines.
My focus remains consistent across projects:
- Reliability: Systems that hold up under real usage
- Scalability: Infrastructure that grows without friction
- Maintainability: Clear, modular, testable code
- Performance: Faster inference, optimised retrieval, efficient design
- Impact: Practical solutions powered by modern AI
Whether it's a microservice architecture or a vector-search pipeline, I aim for clarity, robustness, and long-term maintainability.
Email: harshilmakhija@outlook.com
LinkedIn: https://www.linkedin.com/in/harshil-makhija-500909353/
X / Twitter: https://twitter.com/MakhijaHarshil
Always learning. Always building.