Hi, I'm Prashant.

AI Engineer

Building intelligent systems — LLMs, RAG pipelines,
and autonomous agents that solve real-world problems.

Prashant Raj Bista — AI Engineer

Profile

Name Prashant Raj Bista

Location Kathmandu, Nepal

Email prashant.bista.18@gmail.com

LinkedIn prashant-raj-bista

GitHub @prashantrajbista

Status Open to opportunities

My Story

Prashant Raj Bista

Building the Future with AI

I'm an AI Engineer currently working full-time at IdeaBoxAI and Azminds Services in Kathmandu. I hold a BE in Electronics, Information & Communication Engineering from Tribhuvan University, IOE, Thapathali Campus.

I specialise in building production-grade AI systems — RAG pipelines, LLM-powered APIs, and generative AI products. My work sits at the intersection of backend engineering and applied AI, turning complex LLM capabilities into reliable, scalable software that solves real-world problems.

5+ AI Projects
2+ Years Coding
10+ Technologies

Technical Skills

Technologies I use to build AI-powered systems

AI & LLMs
LangChain LlamaIndex OpenAI API Claude API HuggingFace Prompt Engineering RAG
ML & Data
PyTorch scikit-learn Pandas NumPy Fine-tuning Embeddings
Backend & APIs
Python FastAPI Django Flask REST APIs WebSockets
Vector DBs & Search
Pinecone ChromaDB Weaviate FAISS PostgreSQL Redis
Infra & Tools
Docker Git AWS Linux CI/CD Nginx
Electronics & Embedded
Arduino Raspberry Pi MATLAB Signal Processing IoT

Featured Projects

AI systems and engineering work I'm proud of

RAG · LLM

Chatbot From PDF

A RAG-based conversational AI that ingests PDF documents, performs semantic search over a custom vector database, and uses Gemini + Mistral to answer questions and automate appointment booking via Gmail.

Python Gemini API Mistral AI Vector DB Streamlit
Computer Vision · Robotics

Autonomous Rubik's Cube Solver

Published at IOEGC15. An autonomous cube-solving system that uses YOLOv8 to detect and virtualise cube state, then drives a single-degree-of-freedom mechanical arm via Arduino to physically execute the solution.

YOLOv8 Python C# Arduino Computer Vision
Computer Vision · ML

Night Jasmine Flower Counter

YOLO-based object detection system for counting Parijat flowers in ground-level imagery. Trained on a custom dataset of ~2000 annotated images (augmented from 117 originals) with a Streamlit web interface.

YOLO Python Streamlit CVAT Jupyter
NLP · Neural MT

Nepali–English Translation with Prosody Preservation

Neural machine translation system that translates Nepali to English while preserving prosodic features — tone, stress, and rhythm — using Facebook's fairseq sequence-to-sequence toolkit.

Python fairseq NLP Neural MT Jupyter

Experience

My journey in engineering and AI

Jun 2025 – Present Full-time · AI Engineering
Junior AI Engineer · IdeaBoxAI

Building production AI systems across the full ML spectrum at IdeaBoxAI. Work spans developing time series forecasting models, classification and regression pipelines, and generative AI products — all served through FastAPI microservices backed by vector databases for semantic retrieval. Deeply embedded in the Anthropic ecosystem, using the Claude API and Claude SDK to build tool-use agents, structured-output pipelines, and context-aware AI features shipped to end users.

Claude API Claude SDK FastAPI Vector DB Time Series Classification Regression Generative AI Python
Dec 2024 – Present Full-time · AI & Backend
Associate Software Engineer · Azminds Services

Working on-site in Kathmandu designing and deploying RAG pipelines and LLM-integrated backend systems for enterprise clients. Responsibilities span building retrieval-augmented generation architectures, fine-tuning and evaluating large language models, developing REST APIs to serve AI features, and ensuring system reliability and performance in production environments.

RAG LLMs Python FastAPI Vector DBs
Apr 2021 – Apr 2025 Education
BE in Electronics, Information & Communication Engineering

Tribhuvan University, IOE, Thapathali Campus · Kathmandu, Nepal. Four-year programme covering signal processing, computer networks, embedded systems, and software engineering — with a final-year focus on applied AI and machine learning projects.

Tribhuvan University IOE Thapathali Campus

Research

Academic projects and research publications

Research Grant · Dec 2023 View Proposal

Deep Generative Modeling for Automated Image Manipulation via Text-Guided Prompts

NCE Research Grant — IOE, Thapathali Campus

PI: Er. Dinesh Baniya Kshatri · Nishan Khanal · Prashant Raj Bista · Nimesh Gopal Pradhan · Abhinav Chalise

Proposed a novel text-driven image editing framework built on Stable Diffusion that addresses two critical gaps in existing methods: simultaneous multi-object editing within a single prompt, and a undo/redo mechanism that removes edits without residual artifacts. Text prompts are parsed with NLP models, segmented into per-object instructions, and applied iteratively through a latent-diffusion pipeline. Evaluated using LPIPS and MS-SSIM metrics on COCO and ImageNet datasets.

Role: Mathematical Modeling for Simultaneous Edits (Linear Algebra, Probability, NLP)

Stable Diffusion NLP CLIP PyTorch Diffusion Models LPIPS
Minor Project · Mar 2024 View Slides

Vision-aided Mechanical Design for an Autonomous Rubik's Cube Solver

Tribhuvan University, IOE, Thapathali Campus — BE Minor Project

Abhinav Chalise · Nimesh Gopal Pradhan · Nishan Khanal · Prashant Raj Bista  |  Supervisor: Er. Dinesh Baniya Kshatri

Built an end-to-end mechatronic system that autonomously solves a scrambled 3×3×3 Rubik's Cube. A webcam feeds raw frames into a YOLOv8 colour-detection model that maps cube faces to a state string; Kociemba's Algorithm computes the optimal move sequence (≤20 moves); an Arduino UNO drives three stepper-motor axes to physically execute each rotation. A companion C# GUI virtualises the cube state in real time.

YOLOv8 Python C# Arduino Kociemba Algorithm Computer Vision Robotics
Review Paper · Aug 2025 View Paper

Recent Developments in SLAM and Drone Autonomy: A Five-Year Perspective

Independent Review — Preprint, August 2025

Prashant Raj Bista · Toshika Ojha

A survey synthesising five years (2020–2025) of progress in Simultaneous Localisation and Mapping (SLAM) and UAV autonomy. Covers resource-constrained SLAM for nano-UAVs (NanoSLAM), dynamic environment adaptations (DynaVINS, DynaGSLAM), depth-image quality improvements for 3D reconstruction, AI-driven drone control via foundation models and LLM-generated command systems, and drift-free localisation through digital twin alignment.

SLAM UAV / Drone ORB-SLAM3 DynaVINS LiDAR Foundation Models LLM Path Planning
Prashant Raj Bista

Let's Talk

Services Connect Open to

Freelance projects · Full-time AI roles · Research collaborations

About

AI Engineer building intelligent systems with LLMs, RAG, and agents. Based in Kathmandu, Nepal. Available for global remote work.

Email

prashant.bista.18@gmail.com