Skip to content
View HarshilMaks's full-sized avatar

Highlights

  • Pro

Block or report HarshilMaks

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
.github/profile/README.md

Harshil Makhija

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.


Professional Interests

Deep Learning • LLMOps • RAG Pipelines • Computer Vision
Backend APIs • Cloud-Native Architecture • System Design
Multi-Agent Systems • Model Serving • Vector Search


Core Stack

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


Professional Ethos

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.


Connect

Email: harshilmakhija@outlook.com
LinkedIn: https://www.linkedin.com/in/harshil-makhija-500909353/
X / Twitter: https://twitter.com/MakhijaHarshil

Always learning. Always building.

Pinned Loading

  1. transformer transformer Public

    Pytorch-Transformer architecture from the “Attention Is  All  You  Need” paper, delivering a clear and focused codebase for hands‑on learning. Engineered for real‑world prototyping, it transparentl…

    Python

  2. EuroSAT-ResNet101 EuroSAT-ResNet101 Public

    A Geo-AI engine for automated ESG and supply chain monitoring. This project uses a ResNet-101 model, fine-tuned on the EuroSAT satellite dataset, to classify land use and detect environmental risks…

    Python

  3. InsightDocs InsightDocs Public

    A multi-agent AI platform for advanced document intelligence. This system orchestrates scalable, asynchronous workflows, using a team of specialized AI agents to manage the entire document lifecycl…

    Python 1