Tenzin Lhakpa AI/ML Engineer
Open to opportunities — 2026

AI/ML
Engineer

I build agentic systems that take manual work off people's plates — autonomous agents built on large language models and retrieval-augmented generation that make organizations measurably more efficient.

01 — Selected Work (05)
№01
Job-Bot — Automated Job Application System

An automation tool that streamlines the job hunt: it searches postings, filters them against your criteria, and submits applications on your behalf.

  • Automated job search and application submission
  • Smart filtering based on job criteria
  • Résumé and cover-letter customization
PythonWeb ScrapingAutomation
Source ↗
Job-Bot automation system Fig. 01 — Job-Bot
№02
RestroBot — Conversational AI for Restaurants

A RAG-based virtual assistant built on GPT-4 that handles reservations and orders with the efficiency of a machine and the courtesy of your best staff member.

  • Handles multiple concurrent customer requests
  • Consistent, accurate, grounded responses
  • Retrieval-augmented generation over menu & policy data
PythonPyTorchLangChainGPT-4 APIPineconeSQLite
Source ↗
RestroBot interface Fig. 02 — RestroBot
№03
Rotatory Machinery Fault Detection

A deep learning model that detects mechanical faults in heavy-industry rotatory machines from their vibration signals.

  • 98% accuracy in fault detection
  • Deployed at Machine Monitoring Systems, LLC
PythonPyTorchAWSPandasNumPyMatplotlib
Source ↗
Fault detection system Fig. 03 — Vibration analysis
№04
FigExtractor — PDF Figure & Caption Extraction

A computer-vision tool that extracts figures and their associated captions from PDF documents — built for assembling LLM training corpora.

  • Detects figures, diagrams, and plots automatically
  • Locates figure boundaries with CV techniques
  • Pairs each figure with its corresponding caption
PythonOpenCVNumPyPILSeleniumlxml
Source ↗
Figure extraction pipeline Fig. 04 — Extraction pipeline
№05
PDFs & Books Harvester

A data-collection tool for assembling large-scale text corpora used in training and fine-tuning large language models.

  • Generates download links from a search term, across pages
  • Downloads hundreds of books in parallel with error handling
  • Fully automated pipeline from search to storage
PythonBeautifulSoup4ThreadPoolExecutor
Source ↗
Book harvesting tool Fig. 05 — Corpus collection
02 — Research (01)
Submitted — ICLR 2025

EndoAssistant: An AI Assistant for Endoscopy Applications

Leverages advanced machine learning to assist medical professionals during endoscopic procedures — providing real-time analysis, anomaly detection, and procedural guidance to improve diagnostic accuracy and treatment outcomes.

Computer Vision Medical AI Deep Learning
Read on OpenReview ↗
EndoAssistant visualization Fig. 06 — EndoAssistant
03 — Essays (01) — more in progress
E·01 This is How I Would Explain How a Transformer Model Works to a Newbie Medium ↗ E·02 Understanding RAG Systems: Beyond Simple Retrieval Coming soon E·03 The Art and Science of Fine-tuning LLMs Coming soon E·04 When Machine Learning is Overkill (and When It Isn't) Coming soon
04 — About Tenzin Lhakpa
Tenzin Lhakpa Fig. 07 — The engineer

I'm passionate about advancing AI through meaningful collaboration, with a focus on building practical solutions that solve real-world challenges. My current work centers on agentic systems — autonomous AI agents that take over repetitive manual work inside organizations and make teams measurably more efficient. Whether it's agent design, computer vision, ML pipelines, or retrieval-augmented generation — I care about work that ships.

My expertise spans from traditional statistical learning to cutting-edge large language models and GenAI applications, with hands-on experience designing RAG architectures that enhance AI's contextual understanding and reliability. I'm committed to creating AI solutions that deliver tangible impact across industries.

ML / AI

  • Large Language Models & fine-tuning
  • RAG systems & AI agents
  • Computer vision · NLP · Transformers

Frameworks

  • PyTorch · LangChain · OpenCV
  • Pandas · NumPy · Scikit-learn

Infrastructure

  • AWS · Docker · Git
  • SQL · REST APIs

Focus areas

  • Agentic systems · Workflow automation
  • Production ML · Conversational AI
  • Data extraction · Research
05 — Contact Response within 24–48h

Have a project, a role, or a research idea? —

tenlhak98@gmail.com