Aashish Pant

Kathmandu, Nepal · UTC+5:45
AI engineer. I build AI agents and machine learning models that people use every day.

1About

ItemDetail
RoleAI engineer
Work onAI agents, large language models (LLMs), machine learning for finance
LocationKathmandu, Nepal · UTC+5:45
Work modeRemote or on-site
CurrentlyDevDash Labs
ToolsPython, OpenAI Agents SDK, LangGraph, LangSmith, PyTorch, XGBoost, CatBoost, FastAPI, Django, PostgreSQL, Docker, AWS, GCP

2Key numbers

WhatHowNumber
Cost of each company research report, cutmeasured with A/B tests>50%
Time for a full trading analysisagents run in parallel<80 s
Signals built from stock and options datafor each stock, during the day400+
Building software that people usesince mid 20233 yr
Fusemachines AI Fellowshipselected from national applicantstop 3%

3Selected work

What I builtWhereWhat it does
Key Account Intelligence agent (designed and built its core)AlkemyResearches a client's most important customers, finds who can introduce them, tracks progress and keeps the news up to date
Introductions agentAlkemyWorks out who knows whom from shared employers and schools, and ranks who can make the best introduction
Lead-finding agentAlkemySearches the web for companies that match a client's ideal customer; found 600+ in one search
Cost reductionAlkemyCut the cost of each report by more than half by giving each agent only what it needs and testing a cheaper model
TradePilotAI prediction modelsDevDashPredict a stock's high, low and price swings for the day from 400+ signals, tested only on later dates so results are honest
TradePilotAI trade-check agentsDevDashCheck news, earnings, insider trades and the economy, and can stop a trade; a full run takes under 80 seconds
Plain English to database queriesResearchA T5 model that also reads the database layout; it beat a model without that on hard MongoDB queries
Crop recommendation from field sensorsIOEWireless sensors read the soil; a machine learning model suggests what to plant
Gift card platform for many businessesAtrustaBuilt end to end: Django REST Framework, React, Tailwind, PostgreSQL, Redis, Celery, live updates over WebSockets, Stripe payments, QR-code redemption, AWS S3, Mailgun email
Booking assistant for a skincare clinicAtrustaBooks appointments for clients and adds them to the clinic's calendar

4Experience

DatesRole
Apr 2024 – nowDevDash Labs, Member of Technical Staff, Applied LLM Systems
2023 – 2024Atrusta, Product Engineer
2023Fusemachines AI Fellow, ML/AI research track
2019 – 2024Bachelor of Engineering in Electronics, Communication and Information EngineeringThapathali Campus, Institute of Engineering, Tribhuvan University. First Division.

5Contact