Building End-to-End ML Pipelines
A practical deep-dive into robust machine learning workflows, from data ingestion to model deployment and monitoring.
Coming SoonLoading Sushan Adhikari's portfolio...
Open to new opportunities
👋Hello, I am
SushanAdhikari — AI/ML Engineer
Computer Engineering graduate (Kathmandu University) with research and industry experience in AI/ML, NLP, Computer Vision, and MLOps. First author on multiple publications and builder of production-focused systems for real users.
3+
Publications
300K+
Users Impacted
2
AI Startups
Scroll Down
About Me
From Research to Production AI Systems
I am a Computer Engineering graduate from Kathmandu University, with an exchange semester at IIT Palakkad, building AI systems that balance research depth with practical deployment.
My work spans ML/MLOps, NLP, Computer Vision, LLMs, and RAG, with first-author publications (ICAIL 2026, KUSET) focused on low-resource language technology, explainability, and rigorous evaluation.
I have contributed to production-scale platforms including Nepal’s national pension system (300k+ users), and as a co-founder I focus on measurable impact, reliable engineering, and systems that work beyond demos.
Education
Kathmandu University (B.Eng.) + IIT Palakkad Exchange
Core Focus
AI/ML, NLP, Computer Vision, and MLOps
Recognition
ICAIL / KUSET Publications, NASA Space Apps, Hult Prize
Stack Used Till Date
Python
Django
React
PyTorch
Scikit-learn
Computer Vision
NVIDIA DeepStream
Triton Inference
GStreamer
YOLOv8
OpenCV
FastAPI
Flask
PostgreSQL
SQL
REST APIs
Data Pipelines
Docker
AWS
EC2
Airflow
Databricks
PySpark
Python
Django
React
PyTorch
Scikit-learn
Computer Vision
NVIDIA DeepStream
Triton Inference
GStreamer
YOLOv8
OpenCV
FastAPI
Flask
PostgreSQL
SQL
REST APIs
Data Pipelines
Docker
AWS
EC2
Airflow
Databricks
PySpark
Python
Django
React
PyTorch
Scikit-learn
Computer Vision
NVIDIA DeepStream
Triton Inference
GStreamer
YOLOv8
OpenCV
FastAPI
Flask
PostgreSQL
SQL
REST APIs
Data Pipelines
Docker
AWS
EC2
Airflow
Databricks
PySpark
Featured Projects
Directional Asymmetry in Low-Resource Legal Machine Translation: A Nepali-English Case Study
- Analyzes direction-dependent performance gaps in Nepali-English legal translation under low-resource constraints.
- Shows where targeted corpus design improves legal MT reliability across source-to-target directions.
Keywords:Legal NLPMachine TranslationLow Resource
Enhancing Ethical Reasoning in Tiny LLMs via Fine-Tuning and Multi-Agent Consensus
- Fine-tunes TinyLlama-1.1B on ethical dilemma datasets to improve decision consistency in constrained models.
- Evaluates a multi-agent consensus pipeline to reduce failure cases and improve reasoning robustness.
Keywords:Tiny LLMsAlignmentMulti-Agent
Detecting Image Forgeries and Deepfakes: A Comparative Study of CNN and Transformer Models
- Compares CNN and transformer architectures for large-scale deepfake and image manipulation detection tasks.
- Benchmarks performance trends over diverse forgery patterns to identify practical deployment trade-offs.
Keywords:Computer VisionDeepfakesBenchmarking
RAG for Theoretical CS Education: Algorithm Analysis and Complexity Theory
- Builds a retrieval-augmented tutoring workflow for algorithm analysis and complexity-theory learning support.
- Combines proof-aware retrieval with LLM reasoning to improve conceptual clarity for advanced CS learners.
Keywords:RAGCS EducationComplexity Theory
Physics-Informed Data Augmentation for Sediment Concentration Prediction in Himalayan Rivers
- Applies physics-informed augmentation to improve sediment concentration prediction in sparse Himalayan river datasets.
- Improves robustness of river-monitoring models under high seasonal variance and limited labeled samples.
Keywords:Physics-Informed MLHydrologyData Augmentation
Automated Mathematical Animation Generation: Dataset Requirements and Validation Gaps
- Studies dataset requirements for reliable LLM-generated Manim outputs in math visualization workflows.
- Identifies validation gaps that affect reproducibility, clarity, and pedagogical accuracy in generated animations.
Keywords:LLMMath AnimationSTEM Education
Explainability Methods for Hybrid CNN-Transformer Document Layout Analysis
- Builds explainability workflows for hybrid CNN-transformer models used in document layout understanding.
- Targets interpretable debugging signals that improve trust, error analysis, and model governance.
Keywords:XAIDocument AIHybrid Models
My Startups
Nurvexa
RAG-powered nursing exam preparation platform
Growing
Co-founded Nurvexa to help nursing students prepare for licensing exams with adaptive question generation and personalized study plans.
RAGCore Engine
PCLExam Focus
2025Founded
NLPRAGData-Driven Learning
PrepGraduate
AI-powered GRE preparation and score analytics
In Development
Co-founded PrepGraduate to deliver adaptive GRE practice, full-length mock testing, and actionable score insights.
GRETarget Exam
AIAdaptive Practice
2026Founded
LLMsAssessment AnalyticsEdTech
Experience and Education
Jan 2026 - Apr 2026
Junior MLOps Developer
KyraWorks
Built CI/CD pipelines using Docker, EC2, AWS, and Terraform for automated model deployment workflows.
Oct 2025 - Jan 2026
Computer Vision Intern
KyraWorks
Deployed and optimized 5+ models on Triton Inference Server and benchmarked DeepStream plus GStreamer for real-time multi-camera processing.
Jan 2025 - Present
AI and Data Engineer (Volunteer)
Mercuri.world
Built an ML recommendation pipeline across 50+ job categories in collaboration with 150+ global volunteers.
Jun 2025 - Oct 2025
Full-Stack Development Intern
National Pension Management System, Nepal
Contributed to a national pension platform (300k+ users), integrated anti-spoofing liveness detection, and supported DB schema design.
Jan 2022 - Feb 2026
B.Eng. Computer Engineering
Kathmandu University, School of Engineering
Completed the B.Eng. with coursework in Computer Vision, Databases, Computer Architecture, and Statistics, alongside first-author AI/ML research.
Jan 2025 - May 2025
Exchange Semester, B.Tech CSE
IIT Palakkad
Completed coursework in Introduction to AI, Linear Algebra, Compiler Design, and Graph Theory and Combinatorics.
My Certifications
Machine Learning Specialization
Andrew Ng — Stanford / Coursera
2026
Andrew Ng's Machine Learning Specialization: supervised and unsupervised learning, neural networks, and applied ML best practices.
Apache Airflow Certifications
Astronomer
2024
Astronomer certifications for Apache Airflow 2 — DAG Authoring and Fundamentals — covering pipeline orchestration and workflow design.
DataCamp Certifications
DataCamp
2025
Tracks in Supervised & Unsupervised Learning, AI Fundamentals, PySpark, and SQL — hands-on ML and data tooling.
Embeddings for NLP
OpenHPI
2025
Embeddings-focused NLP course covering semantic representations and retrieval use cases.
Awards and Achievements
Hult Prize OnCampus Winner
Kathmandu University
Led a computer-vision pipeline for fish-disease classification (Dr.Fish) and represented Nepal at the Hult Prize Regional Summit in Bangkok.
NASA Space Apps People’s Choice Winner
2024
Recognized for Cosmira, an interactive educational web app built for science outreach and engagement.
ICT Awards 2024 Finalist
Rising Star Innovation Category
Selected as finalist for impactful technical innovation and applied AI product execution.
AI Crusade 2023 Winner
Health Track
Won health track with MastiskaTrack, an AI-assisted mental health assessment solution.
Conference and Acceptance Records
USC, NCCI, ICAIL, LEC
Attendance certificates and acceptance proof for ongoing and published research contributions.
Mahatma Gandhi Scholarship
Embassy of India, Nepal
Awarded for academic excellence and strong merit performance during earlier studies.
KU Integration Bee Semi-Finalist
Mathematics Competition
Reached semi-finals in Nepal’s early integration-bee competitions, demonstrating strong mathematical fluency.
Featured In
NASA Space Apps
Hult Prize
Kantipur Media
TechPana
Kathmandu UniversityNASA Space AppsHult PrizeKantipur MediaTechPanaKathmandu UniversityNASA Space AppsHult PrizeKantipur MediaTechPanaKathmandu UniversityMentor Testimonials
My Blog
Machine Learning
NLP
The Art of Fine-Tuning LLMs
Lessons from adapting large language models for task-specific outcomes, grounded in low-resource legal NLP work.
Coming Soon
DevOps
DevOps for ML
How Docker, Terraform, and CI/CD can accelerate reproducibility, deployment velocity, and ML model lifecycle quality.
Coming SoonLet's Connect
Ready to collaborate?
I am always open to discussing opportunities, research collaborations, or impactful engineering work. If you have something in mind, let us talk.
Location
Dhulikhel, Kavre, Nepal
Phone
Languages
English, Nepali, Hindi