Hi, I'm Prashant.
AI Engineer
Building intelligent systems — LLMs, RAG pipelines,
and autonomous agents that solve real-world problems.
Profile
Name Prashant Raj Bista
Location Biratnagar, Nepal
Email prashant.bista.18@gmail.com
LinkedIn prashantrajbista
GitHub @prashantrajbista
Medium @prashantrajbista
Status Open to opportunities
My Story
Building the Future with AI
I'm an AI Engineer from Biratnagar, Nepal, with full-time experience at IdeaBoxAI and Azminds Services. 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.
Technical Skills
Technologies I use to build AI-powered systems
AI & LLMs
ML & Data
Backend & APIs
Vector DBs & Search
Infra & Tools
Electronics & Embedded
Featured Projects
AI systems and engineering work I'm proud of
LLM Misuse Monitor
Async monitoring service that flags jailbreaks, prompt injection, and PII leakage in self-hosted LLM traffic. Cross-session risk-scoring engine catches slow-burn misuse missed by single-message filters, with Llama Guard 3, Presidio, and LLM Guard as pluggable detectors and a triage dashboard.
Experience
My journey in engineering and AI
Junior AI Engineer · IdeaBoxAI
Built FastAPI microservices for a multi-tenant AI platform with credit-based usage metering. Developed a demand forecasting product using ClickHouse APIs and LangGraph ML pipelines, and trained time-series models for demand planning, shipment-delay prediction, and supplier ranking. Shipped an LLM app comparing multilingual packaging-label PDFs with OCR extraction, and added Langfuse observability, Redis caching, and streaming across GenAI services.
Research Training Programme 2025 · Nepal Research and Collaboration Center (NRCC)
Learned research methodology and academic writing fundamentals, and completed a review paper on SLAM and drone autonomy.
Associate Software Engineer · Azminds Services
Built a RAG chatbot answering queries from multiple sources — databases, PDFs, and web search. Developed backend systems and data-scraping pipelines using Databricks and Apache Spark, and delivered client demos for chatbot-style AI applications.
AI Fellowship 2024 · FuseMachines Nepal
Studied machine learning and deep learning under the guidance of FuseMachines instructors and completed a capstone project as part of the fellowship.
Electronics and Computer Community Amidst Students (ECAST)
Served as Software Coordinator (Jul 2022 – Jul 2023), Vice President (Jul 2023 – Jul 2024), and Consultant (Apr 2024 – Apr 2025).
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.
Research
Academic projects and research publications
Nepali-to-English Speech Translation with Prosody Preservation
Tribhuvan University, IOE, Thapathali Campus — BE Major Project Final Report
An end-to-end speech-to-speech translation pipeline that converts Nepali spoken audio to natural-sounding English speech while preserving prosodic features — tone, stress, and rhythm. The system chains three state-of-the-art models: wav2vec 2.0 for Nepali ASR (fine-tuned on SLR143, SLR43 and Mozilla Common Voice), mBART for Nepali-to-English neural machine translation (fine-tuned on a manually curated parallel corpus), and F5-TTS for prosody-aware English speech synthesis. A custom parallel Nepali–English audio dataset was created to train and evaluate prosody transfer.
Deep Generative Modeling for Automated Image Manipulation via Text-Guided Prompts
NCE Research Grant — IOE, Thapathali Campus
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)
Vision-aided Mechanical Design for an Autonomous Rubik's Cube Solver
Tribhuvan University, IOE, Thapathali Campus — BE Minor Project
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.
Recent Developments in SLAM and Drone Autonomy: A Five-Year Perspective
Independent Review — Preprint, August 2025
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.
Let's Talk
Freelance projects · Full-time AI roles · Research collaborations
AI Engineer building intelligent systems with LLMs, RAG, and agents. Based in Biratnagar, Nepal. Available for global remote work.
Email