Hi, I’m Prashant.
I build backend systems and explore machine learning.
Backend-focused software developer with hands-on experience in Django and FastAPI, a published research paper in machine learning, and a love for travelling, biking, photography, and reading.
Who am I?
I’m a backend-focused software developer who enjoys building reliable, maintainable systems. I’ve worked with APIs, databases, and services, and I’m actively exploring machine learning — both through self-driven projects and research, which led to a published paper on surface roughness prediction using ML.
Outside of work and learning, I love travelling to new places, going on bike rides, taking photos, and reading books across tech, philosophy, and non-fiction. I like combining discipline in my craft with curiosity about how the world works.
What I work with
A snapshot of the tools and technologies I’m comfortable with.
Backend
Data & ML
Infrastructure & Tools
Where I’ve worked
Some highlights from my journey so far.
- Developing and maintaining RESTful APIs with FastAPI and secure user authentication.
- Integrating LLM models to automate candidate profile creation and ranking.
- Optimizing server performance and reducing latency, improving product responsiveness.
- Collaborating with frontend and product teams to deliver scalable features.
- Implemented backend solutions with Django, improving system stability and scalability.
- Reduced bugs through rigorous debugging, testing, and refactoring.
- Managed deployments and NGINX server configurations for smooth rollouts.
Things I’ve built
A mix of backend and ML projects.
Backend
A real estate web application built using Python and Django with Jinja templates. Deployed on a cloud droplet with SSH configuration, database setup, Gunicorn, and NGINX for a production-ready environment.
Web application that generates AI-powered blog content using the OpenAI API. Includes user-friendly UI, prompt configuration, and content management.
Machine Learning & Data
Built machine learning models to predict surface roughness of AISI 304 steel in nanofluid-assisted turning, optimizing machining parameters based on R², RMSE, and MSE metrics.
A collection of smaller ML experiments including classification, regression, and data analysis tasks, used to explore new techniques and improve intuition around models.
Published work
A quick overview of my research paper.
This work applies machine learning models to predict surface roughness during nanofluid-assisted turning of AISI 304 steel. By learning from experimental data, the models help optimize cutting parameters and improve machining quality.
- Developed and evaluated multiple ML models for surface roughness prediction.
- Used R², RMSE, and MSE metrics to quantify predictive performance.
- Demonstrated how ML can support smarter, data-driven manufacturing.
On the road
Some routes, places, and moments I’ve enjoyed.
More rides & stories coming soon 🚀
What I’ve been reading
A few books that left an impact.
Let’s talk
Whether it’s backend work, ML ideas, or just bikes & books.