About Me
Hello! I’m Bibek from Nepal. I’m a Full-Stack AI Engineer who enjoys the craft of shipping end-to-end AI products, from document understanding and RAG pipelines to agentic AI systems, desktop apps to web platforms, and air-gapped deployments to cloud-based enterprise solutions.
At NeoALI, I’m shipping on-device AI desktop applications used by 100+ users, building web-based AI solutions for office workflows, and developing secure, isolated agent sandboxes with default-deny egress using OpenShell, currently piloting with enterprise clients.
I’m a firm believer in my mantra, “If they can do it, I can do it.”
If you would rather not read this entire page, feel free to chat with my chatbot widget at the bottom right.
Technical Skills
Languages
Python
TypeScript
JavaScript
Frontend
React
Next.js
Vite
Electron
Backend APIs
FastAPI
Express.js
GraphQL
Celery
SSE / WebSockets
AI & ML
PyTorch
vLLM
Ollama
IPEX-LLM
Llama-cpp
OpenVINO/OVMS
HuggingFace
Infrastructure
Docker/Compose
Nginx
Linux
GitHub Actions
Airflow
AWS
Google Cloud
Databases & Tools
Redis
PostgreSQL
MongoDB
Qdrant
PyInstaller
Locust
Highlighted Projects
KhururuAI: Work in flow (khururu.com)
A free-to-use AI platform where an LLM router dispatches requests to six specialists that turn plain-language intent into researched answers, decks, documents, code, and images. It runs on pooled free-tier capacity, so anyone can use it without paying or signing up.
Bintech International (bintechint.com)
Shipped a B2B hardware supplier's site solo, covering the storefront, a Payload CMS + Postgres CRM that non-technical staff run themselves, and an AI assistant grounded in the live catalogue so it only quotes real products, prices and stock. Self-hosted on Docker Compose behind Caddy, with the domain, DNS and email managed by me as well.
Charak: Medical Research Assistant (charak.khururu.com)
Answers natural-language clinical questions with cited responses, retrieving live from PubMed and ClinicalTrials.gov v2 and charting results. Code
Work Experience
AI Researcher & On-device Team Lead at NeoALI Co. Ltd, Korea
Aug, 2023 - Present
AI Products
- Technical lead of a 3-member on-device AI team, driving architecture decisions, deployment strategy, and cross-product engineering initiatives.
- Built and shipped SamuGen and SamuGen Plug-in (built on top of my weekend project B-Assist), on-device AI desktop writing assistants used by 100+ users across air-gapped and B2C environments, supporting document-aware AI writing, Doc QnA, and HWP/HWPX/DOCX import/export, with a production-ready web version for on-premise deployment.
- Architected the backend of NeoClaw, an on-premise agentic proposal evaluation platform orchestrating scoring, summarization, synthesis, and ranking subagents, with QnA for querying AI scores.
- Designed and developed SlideGen, an on-premise LLM-powered slide generation and editing platform that creates presentations from uploaded documents with support for PPTX export.
- Won first place globally for our on-device apps at the Intel AI PC Innovation Challenge 2025.
- Built a unified agentic chat interface as the entrypoint across all on-premise AI products, with workflow orchestration that routes user intent to appropriate backends including proposal evaluation, RAG QnA, document translation, and other services.
- Engineered an internal service that sandboxes the pi harness inside per-user/per-session OpenShell containers with default-deny egress, giving an enterprise RAG chatbot secure, isolated agentic task execution via a streaming API.
- Designed backend architecture using FastAPI, Express, Redis, SSE, authentication services, and API gateways, serving as shared infrastructure across multiple AI products.
- Operated shared LLM-serving infrastructure using vLLM, exposing OpenAI-compatible APIs for language models, embeddings, and reranking, serving as shared backend across 5 internal products. For on-device deployment, switched between IPEX-LLM Ollama, Llama-cpp, and OpenVINO.
- Contributed core components to ALIParse (in-house library), including layout analysis, reading-order ranking, document parsing, semantic retrieval, and RAG pipelines.
- Developed neural-network-based Layout Detector (306M), labels: [text, title, list, figure, table]. Two versions: fast (TensorRT-10FPS in T4GPU) vs slow (OpenVINO-1FPS in CPU) for BATCH_SIZE=1.
- Developed fast-header detection model for selectable PDFs that uses font-attributes (name, color, flag), drawings (lines & rects) and header regex patterns.
- Secured 5th position in AI Grand Challenge 2023 (agc2023). My role was to make a Docker image that runs 4 models (1 polyglot and 3 Llama) efficiently within a 40GB image size constraint for offline inference on V100 GPUs.
- Led deployment of AI desktop applications to 50+ air-gapped military notebooks, implementing offline license activation, model distribution, code obfuscation, and enterprise installation workflows.
- Built CI/CD pipelines, cross-platform packaging (Windows/macOS), monitoring dashboards, Slack-based alerting, load and stress testing, product download portals, and SMTP email workflows.
Student Assistant at International Scholar and Student Services (ISSS), KAIST
Mar, 2023 - Aug, 2023
Assisted international students and visitors at the International Scholar and Student Services (ISSS) office by providing accurate information and guidance, ensuring they received the right support and were directed to the relevant staff members. I also volunteered in the preparation and organization of international community events such as KAISTONE.
Researcher Intern at Robust Intelligence & Robotics Lab, KAIST
Jul, 2022 - Dec, 2022
Worked on developing a combined framework for real-time 6D Pose Estimation and Scene Graph Generation (SGG) in Robotic Manipulation Task. I used Cosypose framework for 6D pose and Neural Motif framework for SGG and performed experiments on custom cup datasets.
- For a single moving camera setup, estimated 6D pose and generated dynamic scene graphs.
- For 2 fixed camera setup, developed a probabilistic multi-view object-pose estimation framework that (i) associates multiple estimation results with scene graphs, (ii) combines pose distributions from single-view based estimators, and (iii) constructs a unified scene graph by predicting a unified pose distribution per object using MC dropout.
- Demo:
Backend Developer Intern at Bisonai, Seoul
Jan, 2022 - Feb, 2022
- Built data pipelines (DAGs) in Airflow to collect DeFi data from various sources like Uniswap, Coingecko and stored them in MongoDB Atlas.
- Implemented backend API server using FastAPI and Strawberry (Python GraphQL Library) to provide DeFi data from MongoDB for users interested in knowing DeFi data from multiple Decentralized Exchanges.
- Gained an in-depth understanding of raw DeFi data and its importance to Bisonai’s ML-based System Trading project.
Project Intern at Interactive Computing Lab,
KAIST
Jul, 2021 - Aug, 2021
- Created a beginner-friendly tutorial on data pre-processing and plot visualization with Vega-Lite and D3.js in ObservableHQ notebooks, teaching data visualization techniques on the JavaScript track.
- Reference: observablehq.com/@ic-dataviz?tab=notebooks
Coordinator and Tutor at A Levels Ex-students Tutoring Center (ETC)
Jul, 2018 - June, 2019
- Taught hourly home tuition classes to A-Level students in Chemistry, Physics, Mathematics and Biology. I reached students by publishing advertisements on hamrobazaar.com and through referrals from my teachers.
Teaching Assistant at British Model College
(BMC)
Jul, 2017 - Oct, 2017 and Feb, 2018 - May, 2018
- Conducted tutorial lectures and help sessions, guiding students through topics they found difficult in Chemistry, Physics, Mathematics and Biology.
- Counseled students with examination tips and college application guidance.
Others:
- Part-time A Levels Tutor at BNS Education Hub, New Road, Kathmandu [Jan, 2018 - Jun, 2019]
- Class Representative (CR) in British Model College for 2 years
- Prefect of Swarnim School during class 10
- Executive Member of Global Peace Young Leaders (GPYL) [Jun, 2018 - Jun 2019]
- General Member of Society of Nepalese Students in Korea (SONSIK) [Sep, 2021 - Sep, 2022]
Education
Bachelor of Electrical Engineering and Computer Science from KAIST, Daejeon, South Korea
(2019 - 2023)
GCE A Levels from British Model College, Kathmandu,
Nepal
(2015 - 2017)
Grade 8-10 from Swarnim School, Kathmandu, Nepal
(2013 - 2015)
Grade Nursery-8 from Khimti Project School, Dolakha,
Nepal
(2002 - 2013)
Achievements
- Intel AI PC Innovation Challenge - First Place (NeoALI, January 2025)
- AI Grand Challenge, IITP - Fifth Place (NeoALI, 2023)
- Awarded KAIplus+ scholarship for Spring Semester 2023
- Won the Social Innovation Award at SDG Hack 11, Tsinghua Global Summer School 2021, for the topic ‘AI to Solve Education Accessibility Problems in Rural Areas’
- Common Purpose Alumni and awarded the badge "Inclusive Leadership 2021"
- Awarded KAIST International Student scholarship with stipends for 4 years [2019-2023]
- Gained the highest mark in Nepal for AS Level Chemistry in Nov, 2016 examination series
- Secured 2nd position in Quiz in Budhanilkantha Inter-School Olympiad, 2016
- Secured 3rd position in Cassini Scientist For a Day Contest, 2017
- Best student of the batch 2015/2017 in British Model College
KAIST Activities
- Student Assistant in International Scholar and Student Services (ISSS) team at KAIST from Spring 2023
- Candidate for 2019-Winter Alma Mater visiting program and conducted KAIST info session at my high-school: LINK
- Video won the ‘Excellence Award’ in the 2020 Happy KAIST UCC Contest for raising awareness about mental health: LINK
- Paper (Idea) won the ‘INSIGHTFUL’ award in the online Public Relations strategy contest, 2020 for KAIST admissions to engage in international communities
- Second winner on the writing contest, ‘What is like studying at KAIST?’ organized by the KAIST Admission Office in December, 2019
- International Community Representative of Nepal for Spring 2020, Spring 2021, Fall 2021, Spring 2022 and Fall 2022
- Online Mentor for new international students of Fall 2020, Spring 2021, Fall 2021 and Spring 2022
- Graduated with 142.0 credits and list of courses taken each semester: course-records