JobGenie
An AI job-search copilot that checks resume fit against each role, simulates ATS scores and tracks applications, grounded by RAG.
Python · FastAPI · Gemini API · RAG · Docker · PostgreSQL
The castle is waking
Saksham Agrawal
Break the seal to enter with music
software engineer · ai/ml
I build full-stack AI systems, from FastAPI backends and deep-learning models to LLM and RAG pipelines, and turn ideas into working applications.
End-to-end AI apps: FastAPI backends, LLM and RAG pipelines, and clean, usable frontends.
Designing, training and benchmarking models from scratch: CNNs, GRU/LSTM and KAN.
FastAPI, REST, relational and vector databases, built with production in mind.
Gemini API, structured outputs, and RAG grounding to cut hallucination in real apps.
It gives you exactly what you need. Here: five things I built.
Every project has its own Daily Prophet front page. Open one to read the full story.
An AI job-search copilot that checks resume fit against each role, simulates ATS scores and tracks applications, grounded by RAG.
Python · FastAPI · Gemini API · RAG · Docker · PostgreSQL
A real-time mobile vishing detector that analyses incoming call audio to catch AI-generated and deepfake voices.
89.68% accuracy
Flutter · TensorFlow · Firebase · Audio
A PyTorch research project comparing GRU, from-scratch KAN and hybrid architectures for next-item e-commerce recommendation.
58.08% HR@10 · 39.42% NDCG@10
Python · PyTorch · GRU + KAN · Deep Learning
A console-based Python app for managing rocket specs, launch schedules and customer bookings, with separate admin and user roles.
Python · Standard library · Flat-file storage · CLI
A team-built Java Swing desktop app that manages books, members and issue and return workflows on a SQL database.
Java · Swing · SQL · Desktop GUI
“Hmm… a new head. Shall I sort you, or tell you about Saksham?”
Python · PyTorch · CNN · Computer Vision · Streamlit
View on GitHub →Field Coordination · Documentation · Community Engagement · Teamwork
The languages, tools and techniques I use to turn ideas into working software.
Gold spells are ones I have used in a real project.
Python is my everyday language, with Java and SQL for desktop and database work, and C for the fundamentals.
Used in JobGenie, Session recommender, Launch Cadence, Library system, IBM internship
Models designed, trained and benchmarked from scratch, and LLMs grounded with RAG so their answers hold up.
Used in JobGenie, Session recommender, PhoniX, IBM internship (custom CNN that beat EfficientNet on macro-F1)
APIs and data stores built with production in mind.
Used in JobGenie
Shipping, packaging and the interfaces people actually click.
Used in JobGenie, IBM internship (Streamlit app in Hindi and English), Library system

I don’t like leaving ideas as ideas. If I can imagine it, I want to build it.
I’m a final-year Computer Science (AI & ML) student at UPES who enjoys turning concepts into real products. From training machine learning models and building FastAPI backends to integrating LLMs with RAG, I love working across the entire stack. Whether it’s JobGenie or my latest experiment, I’m always chasing the next problem worth solving.
Outside of building, you’ll usually find me solving DSA, exploring new technologies, or figuring out how to make software just a little smarter.
UPES · Office of the Registrar
Relevant coursework: Machine Learning · Pattern & Visual Recognition · Deep Learning · Data Structures & Algorithms · Database Management Systems · Operating Systems.
Opening the ledger…
Have something that needs to be built? Open to freelance and full-time opportunities. Reach out about a role, a project, or just to talk shop. I read everything myself.
Thank you. I read every one myself and will write back soon.