Meghana Bhange, Developer in Montreal, QC, Canada
Meghana is available for hire
Hire Meghana

Meghana Bhange

Verified Expert  in Engineering

Software Developer

Location
Montreal, QC, Canada
Toptal Member Since
October 27, 2022

Meghana是一名机器学习工程师，热衷于以数据驱动的方式解决问题. 她目前正在可信信息系统实验室攻读硕士学位，研究重点是隐私保护技术, ÉTS Montréal. 她在自然语言处理方面有经验，之前曾在SemEval-2020上发表过作品. Meghana热衷于从事创造性项目，并总是寻找新的方法来应用她的技能.

Natural Language Processing (NLP)Artificial Intelligence (AI)Machine LearningDeep LearningPythonAI DesignLarge Language Models (LLMs)Data EngineeringChatbotsOpenAIPandasScikit-learnData PipelinesPostgreSQLAmazon S3 (AWS S3)GPT-3ChatGPTPrompt EngineeringStable DiffusionCryptographyDall-ELangChainSpeech RecognitionComputational LinguisticsSpaCy

Portfolio

UInclude, Inc
Natural Language Processing (NLP), Machine Learning, GPT...
TISL Lab at ETS Montreal
Python 3, Artificial Intelligence (AI), Scikit-learn
Freelance Client
Artificial Intelligence (AI), Chatbots, OpenAI GPT-3 API...

Experience

Natural Language Processing (NLP) - 4 yearsPython - 2 yearsKubernetes - 2 yearsMachine Learning - 2 yearsGPT - 2 yearsDjango - 1 yearSQL - 1 yearAmazon SageMaker - 1 year

Availability

Part-time

Preferred Environment

生成预训练变形器(GPT)，自然语言处理(NLP)，人工智能设计

The most amazing...

...我参与的项目是开发一个端到端的自定义识别服务，该服务基于资源受限的代码混合设置，具有低延迟需求.

Work Experience

AI Engineer

2023 - PRESENT
UInclude, Inc
  • 利用SpaCy和基于规则的引擎开发了一个特定于上下文的偏倚词匹配模型，以识别工作列表中的偏倚词.
  • 使用句子转换器和GPT-3创建了同义词扩充器，以发现上下文特定的同义词, replacing biased words in job listings with unbiased alternatives.
  • 使用AWS上的FastAPI端点部署模型，同时通过DynamoDB存储和查询数据.
Technologies: Natural Language Processing (NLP), Machine Learning, GPT, Generative Pre-trained Transformers (GPT), Amazon Web Services (AWS), Deep Learning, Python, TensorFlow, Scikit-learn, Amazon DynamoDB, Amazon S3 (AWS S3), FastAPI, SpaCy

Researcher

2022 - PRESENT
TISL Lab at ETS Montreal
  • 研究了一个投诉申诉系统的隐私保护ML和数据发布.
  • 研究了基于反事实解释api的机器学习系统的模型提取攻击.
  • 建模一个可以利用反事实解释提供的信息来构建高保真度和高精度模型提取攻击的对手.
  • Benchmarked the model performance on the Folktables dataset, with the extracted model gaining fidelity of around 97.6%.
Technologies: Python 3, Artificial Intelligence (AI), Scikit-learn

AI Developer

2023 - 2023
Freelance Client
  • 为家长和学生定制的基于GPT-4的聊天界面开发了fastapi端点. 成功地在DigitalOcean上部署了应用程序，确保了强大的性能和可扩展性.
  • Enhanced the chat endpoints by integrating it with LangChain, incorporating plugins like Wikipedia, Search, and Math. This integration improved the reliability of information.
  • 利用矢量数据库查询文档，提高信息检索的可靠性. 开发了能够分析聊天历史以提取相关主题和概念的端点.
Technologies: Artificial Intelligence (AI), Chatbots, OpenAI GPT-3 API, Generative Pre-trained Transformers (GPT), ChatGPT, LangChain

OpenAI Developer

2023 - 2023
Zurney.app
  • 构建一个集成了GPT-3 API的FastAPI后端，生成旅行行程并提取地点. These locations were then geo-encoded with co-ordinates.
  • Built a Next.js应用程序显示旅行行程，并显示谷歌地图上的地理位置颜色代码对应的日子在旅行和有关每个位置的信息.
  • Dockerized and deployed both the FastAPI back end and Next.js front end to DigitalOcean.
Technologies: Artificial Intelligence (AI), ChatGPT, OpenAI, Next.js, FastAPI, DigitalOcean, Large Language Models (LLMs), Natural Language Processing (NLP), Generative Pre-trained Transformers (GPT), GPT, Web Development, OpenAI GPT-3 API

Machine Learning Engineer

2021 - 2022
Hunters.ai
  • 研究并构建用于评估威胁搜索检测器和理解检测输出中的异常模式的分析工具.
  • 组织机器学习检测器的监控和质量检查基础设施.
  • Created a framework for deep investigation of threats.
Technologies: Python 3, Machine Learning, SQL, Artificial Intelligence (AI), Deep Learning, Scikit-learn, AI Design, Machine Learning Operations (MLOps), Amazon SageMaker, Kubernetes, APIs, Data Pipelines, Amazon Web Services (AWS), PostgreSQL, Data Engineering, Amazon S3 (AWS S3), Amazon DynamoDB

Machine Learning Engineer

2020 - 2021
The Verloop.io
  • 对意图识别服务做出贡献，使用句子转换器提高top-K的查全率和准确率, which improved F1 by 40% absolute.
  • 设计、构建并部署跨所有客户端的多语言名称识别服务.
  • 评估各种语言模型(如ULMFiT和VAMPIRE)在低资源语言上下文中的性能.
  • 使用生成式预训练变压器3 (GPT3)人工智能在聊天机器人中为FAQ系统创建合成训练数据.
Technologies: Machine Learning, Python 3, Pandas, SpaCy, Chatbots, OpenAI, Artificial Intelligence (AI), Deep Learning, Scikit-learn, AI Design, Django, Google Cloud, Google Cloud Platform (GCP), Speech Recognition, APIs, Web Development, Text Generation, Language Models, Large Language Models (LLMs), Flask, Data Pipelines, Machine Learning Operations (MLOps), Computational Linguistics, DaVinci, Generative Pre-trained Transformers (GPT), PostgreSQL

Machine Learning Intern

2019 - 2019
The Verloop.io
  • Created a person-name extractor customized for multilingual conversations. Tweaked Flair, Facebook's natural language processing library, to work on low-latency use cases in English, Spanish, and French.
  • 与之前部署的FastText模式相比，最终模型在F1中的效率提高了47%.
  • 将开发的多语言名称提取器部署到生产环境中，总延迟低于500毫秒.
Technologies: Artificial Intelligence (AI), Chatbots, Deep Learning, Scikit-learn, Text Generation, Language Models, Large Language Models (LLMs), Flask, PostgreSQL

Model Extraction Attack Using Counterfactual Explanation

这是我与ETS蒙特利尔可信信息系统实验室合作的一个研究项目. 我们研究了模型攻击者如何利用反事实解释提供的信息来构建高保真度和高精度的模型提取攻击.

LitNER | Literature Named Entity Recognition

http://github.com/meghanabhange/litNER
Named entity recognition based on Spacy3 trained on the LitBank dataset. 该项目使用Roberta XLM作为基础模型和经过微调的文献数据来理解文献中常用的术语. 该项目发布的预训练模型也可用于对任何文学文本执行NER任务.

Hinglish Twitter Sentiment Detection | SemEval2020

http://arxiv.org/abs/2008.09820
This work adds two common approaches, fine-tuning large transformer models and sample efficient methods like ULMFiT. 先前的工作证明了经典ML方法对极性检测的有效性. We fine-tuned general-purpose languages representation models, such as those of the BERT family, 哪些是与经典机器学习和集成方法一起进行基准测试的. We showed that NB-SVM beats RoBERTa by 6.2%. 表现最好的模型是多数投票集成模型，其F1值为0.707.

Wikipedia Textbook Assistant

http://github.com/meghanabhange/Wikipedia-Textbook-Assistant
简单的流光应用程序与教科书配对，以便人们可以轻松地从他们正在阅读的文本中提取关键短语，并从维基百科获得详细信息，以了解相关上下文.

人工精神错乱(稳定扩散反人类卡牌)| total Hackathon

Artificial Insanity is a multiplayer game for the Toptal Hackathon, which uses Stable Diffusion to generate image responses for a text prompt. In each round, a player chooses prompt, 和其他玩家使用集成的稳定扩散界面生成响应.

我根据DALLE和Stable Diffusion的质量和延迟对性能进行了基准测试. Also, 我在FastAPI上部署了最终的模型，使其更容易与后端的其余部分集成. The solution won the second prize in the Hackathon.

Languages

Python, SQL, Python 3

Other

Machine Learning, Natural Language Processing (NLP), Artificial Intelligence (AI), Deep Learning, APIs, Text Generation, Language Models, GPT, Data Engineering, Chatbots, OpenAI, AI Design, Machine Learning Operations (MLOps), Large Language Models (LLMs), Computational Linguistics, Generative Pre-trained Transformers (GPT), OpenAI GPT-3 API, Research, Transfer Learning, BERT, Signals, Information Theory, Custom BERT, Stable Diffusion, DALL-E, FastAPI, Inference API, Speech Recognition, Web Development, DaVinci, Systems, ChatGPT, Cryptography, Information Technology, Prompt Engineering, LangChain

Frameworks

Django, Flask, Streamlit, Next.js

Libraries/APIs

Pandas, Scikit-learn, SpaCy, TensorFlow

Storage

Data Pipelines, PostgreSQL, Amazon S3 (AWS S3), Amazon DynamoDB, Google Cloud

Tools

Slack, Named-entity Recognition (NER), Amazon SageMaker

Platforms

Kubernetes, Google Cloud Platform (GCP), Amazon Web Services (AWS), Visual Studio Code (VS Code), DigitalOcean, AWS Lambda

Industry Expertise

Cybersecurity

2023 - 2023

Master's Degree (Ongoing) in Information Technology Engineering

École de Technologie Supérieure - Montreal, Canada

2016 - 2020

Bachelor's Degree in Electronics and Telecommunication Engineering

Savitribai Phule Pune University - Pune, India

Collaboration That Works

How to Work with Toptal

在数小时内，而不是数周或数月，我们的网络将为您直接匹配全球行业专家.

1

Share your needs

在与Toptal领域专家的电话中讨论您的需求并细化您的范围.
2

Choose your talent

在24小时内获得专业匹配人才的简短列表，以进行审查，面试和选择.
3

Start your risk-free talent trial

Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.

Top talent is in high demand.

Start hiring