AI engineer in Kathmandu, Nepal

Sushank Ghimire

I build agents that call tools and drive browsers, retrieval systems that survive messy documents, and the FastAPI backends that keep them at 99.9% uptime.

Right now: Software Development Engineer II at Renegade Insurance.

See the workRead the writing
Sushank Ghimire smiling in sunglasses and a red checked shirt
  1. userPull the deductible and effective date from this 41 page policy PDF.request
  2. planDocument is scanned. Run OCR, locate the declarations page, then extract typed fields.312 ms
  3. tool_callocr_document(pages="all", engine="layout")tool_call
  4. observation41 pages, 2 tables detected, declarations page = 32.4 s
  5. tool_callextract_fields(page=3, schema=PolicyDeclarations)tool_call
  6. observation{ deductible: "$2,500", effective_date: "2026-03-01", confidence: 0.97 }840 ms
  7. reflectDeductible matches the premium table on page 7. No schema mismatch. Done.1 pass
  8. finalDeductible $2,500, effective 1 March 2026. Source: page 3, verified against page 7.1,912 tokens

What I build

Agents, retrieval, browser automation and the backends behind them. All of it runs in production.

  1. 01

    Agentic systems

    Tool-calling agents with reflection loops, orchestration and hard limits on retries, budgets and timeouts. Built on Claude and OpenAI, mostly through AWS Bedrock.

    Tool calling, Orchestration, Bedrock

  2. 02

    Retrieval and document intelligence

    RAG pipelines for messy HTML and scanned documents: structure-aware chunking, hybrid retrieval, re-ranking, and multimodal extraction with OCR.

    RAG, OCR, Re-ranking

  3. 03

    Browser automation

    Agents that read the live DOM and complete multi-step workflows in web apps that have no API.

    RPA, Dynamic DOM, Playwright

  4. 04

    Production backends

    FastAPI and Django services with observability, caching and error handling that hold 99.9% uptime under real traffic.

    FastAPI, Django, PostgreSQL

Three AI systems in production

From the last two years. Client details are private, so I describe the engineering only.

Case study 01Verisk Nepal

Agentic document intelligence on AWS Bedrock

Insurance analysts needed answers grounded in thousands of HTML documents, and the first chatbot was slow and often wrong.

  • Claude on Bedrock with tool calling, retrieval, reflection loops and an orchestrator that routes between specialised agents.
  • A preprocessing pipeline for HTML: boilerplate removal, structure-aware chunking and metadata extraction.
  • Hybrid retrieval (lexical plus dense) with re-ranking, response caching and parallel tool execution.
  • A FastAPI redesign with per-tool deadlines, retry budgets, schema validation and tracing.

AWS Bedrock, Claude, FastAPI, PostgreSQL, Python

faster and more accurate
2x
increase in user retention
80%
uptime after the redesign
99.9%

Case study 02Renegade Insurance

Agents that operate insurance web portals

Insurance operations run on third-party portals with no APIs. Every quote, policy lookup and document pull was a person clicking through forms.

  • Browser automation agents that plan, act and observe in a loop, reading the live DOM instead of relying on brittle selectors.
  • Multimodal extraction that combines OCR with vision-capable LLMs to turn scanned forms and tables into typed records.
  • Agentic SEO pipelines for keyword research, competitor analysis and metadata generation.

Python, Playwright, Multimodal LLMs, OCR, FastAPI

Multi-step workflows completed unattended
Structured data from unstructured documents

Case study 03Naamche (reAlpha)

Conversational AI for real estate

A US real estate platform wanted assistants that could answer buyer questions and read listing documents at scale.

  • Chatbots and agentic workflows on OpenAI and Claude via Bedrock, each tuned to a client use case.
  • Document extraction and parsing with NLP to automate data entry from listings and contracts.
  • FastAPI and Django services that exposed the models as reliable, versioned endpoints.

OpenAI, Claude, FastAPI, Django, PostgreSQL

Assistants tuned to each client's use case
Automated document processing

Open source and side projects

Things I built to learn and to ship.

All projects
2023AI / ML

EZ-Crossword

Solves newspaper crosswords and generates new ones with transformer QA models

  • Python
  • PyTorch
  • Transformers
  • Django
  • FastAPI
  • Bootstrap
Details Live Code
2024Web / backend

PokeQuery

Async FastAPI service that caches the PokeAPI into PostgreSQL and serves filtered queries

  • Python
  • FastAPI
  • PostgreSQL
  • asyncpg
Details Code
2025Web / backend

FastTrackV2

Django 5 and DRF rebuild of an engineering institute's platform with Docker, uv and a justfile

  • Python 3.13
  • Django 5.1
  • Django REST Framework
  • PostgreSQL 17
Details Code
2024AI / ML

GenAI 360

Working notes and re-implemented exercises from the Activeloop GenAI course, ported to LangChain 0.2

  • Python
  • LangChain
  • Deep Lake
  • OpenAI
Details Code

Also built

Other work I have shipped along the way

Machine learning studies from my degree

Six studies from my engineering degree. Each one has a notebook and a write-up.

Read the studies

Where I have worked

From backend developer to AI engineer, with a lot of shipped software in between.

  1. Jul 2026 to presentCurrent role

    Software Development Engineer II at Renegade Insurance

    Agents that operate real web applications and read real documents for insurance operations.

    • Built production browser automation and RPA agents that plan and act in a loop and handle dynamic DOM changes, so multi-step web workflows run without a human at the keyboard.
    • Developed end-to-end document parsing and extraction pipelines using multimodal LLMs and OCR to pull structured data out of unstructured documents and tables.
    • Automated SEO work end to end with agentic flows for keyword research, competitor analysis, and metadata and content generation.

    Agents, Browser automation, Multimodal extraction, Python

  2. Jul 2025 to Jul 2026

    Software Engineer II at Verisk Nepal

    Agentic systems on AWS Bedrock with Claude for client-specific insurance workflows.

    • Built production agentic systems on AWS Bedrock using Anthropic Claude with tool calling, RAG, reflection loops and agent orchestration.
    • Designed preprocessing pipelines for HTML documents with smart chunking and metadata extraction to feed high-quality RAG datasets.
    • Doubled chatbot and agent performance on both latency and accuracy through prompt optimization, hybrid retrieval with re-ranking, caching and parallelization. User retention rose 80%.
    • Found and fixed critical backend gaps (rate limits, timeout cascades, tool schema mismatches) and redesigned the FastAPI services with proper error handling and observability, reaching 99.9% uptime.

    AWS Bedrock, Claude, RAG, FastAPI

  3. Sep 2024 to Jul 2025

    Applied AI Engineer at Naamche Inc. (reAlpha)

    Conversational AI and document systems for a US real estate technology company.

    • Designed conversational AI systems on OpenAI APIs and Anthropic Claude via AWS Bedrock, shipping chatbots and agentic workflows tailored to each client.
    • Engineered document extraction and parsing systems that used NLP techniques to automate data processing.
    • Built the FastAPI and Django backend services that put those models in front of production traffic.

    OpenAI, Claude, FastAPI, Django

  4. Mar 2024 to Sep 2024

    AI Developer at ICEBRKR, Virtly

    Research and prototyping across computer vision and NLP.

    • Researched and prototyped AI solutions for business problems in natural language processing and computer vision.
    • Integrated CV and NLP components into products for real-time data analysis and user interaction.

    Computer vision, NLP, PyTorch

  5. Jan 2024 to presentCurrent role

    Technical Head at Fast Track Engineering Institute

    Owns the institute's web platform and infrastructure.

    • Designed and built the institute's website and secure Django backend from scratch.
    • Cut latency by 20% through query optimization, caching and a cleaner deployment pipeline on the VPS.

    Django, PostgreSQL, Nginx

  6. Feb 2023 to Feb 2024

    Backend Developer at Perigee Solutions

    Backend for payroll systems, admin dashboards and business sites.

    • Built payroll management, admin dashboards and business websites with user management, reporting and workflow automation.
    • Integrated REST APIs with frontend teams and improved performance, security and reliability across multiple client projects.

    Django, REST, PostgreSQL

Education

Bachelor of Engineering in Computer Engineering

Thapathali Campus, Institute of Engineering, Tribhuvan University. Kathmandu, Nepal.

2019 to 202375% aggregate

Tools I reach for

What I use now. It changes when something better proves itself.

AI and ML

Anthropic Claude, OpenAI, AWS Bedrock, LangChain, LlamaIndex, PyTorch, TensorFlow, scikit-learn, YOLO, Hugging Face Transformers

Backend

FastAPI, Django, Django REST Framework, PostgreSQL, MongoDB, Redis, Alembic

Languages

Python, TypeScript, JavaScript, SQL

Infrastructure

Docker, Nginx, AWS, GitHub Actions, Cloudflare, Linux VPS

Practices

Hybrid retrieval and re-ranking, Evaluation sets, Observability, Prompt optimization, Caching and parallelization

Notes from building agents and retrieval systems

Write-ups on what broke and what fixed it.

All posts

Working on agents, retrieval or document intelligence? Let's talk.

I'm an AI engineer in Kathmandu and I work with teams around the world. I answer email within a day, and I'm glad to look at a hard problem before we talk about anything else.

[email protected]Download CV
Portrait of Sushank Ghimire, AI engineer in Kathmandu, Nepal
Kathmandu, UTC+5:45