Bhavya Soni

Bhavya Soni

$15/hr
Python, Flask, FastAPI, Docker, LLM, AI, Langchain, OpenAI, Groq
Reply rate:
-
Availability:
Hourly ($/hour)
Location:
Ahmedabad, Gujarat, India
Experience:
3 years
Bhavya Soni - - Linkedin GitHub TECHNICAL SKILLS Programming Languages: Python Frameworks & Libraries: Flask, FastAPI, Pytest, Docker, Celery, RabbitMQ, Numpy, Pandas, Pydantic Databasae & Tools: PostgreSQL, MongoDB, Grafana, Git, GitHub, Bitbucket Generative AI: Prompt Engineering, Large Language Models, RAG, LLM Agents and Tools, Vector Database, Langchain, LlamaIndex, Unstructured.io, Vectara, Amazon Bedrock, Hugging Face WORK EXPERIENCE Software Engineer Crest Data, Ahmedabad, India • • • • • • • • • • • Netskope Cloud Exchange Played a key role in the development of the Netskope Cloud Exchange platform. Designed and implemented a highly efficient data retrieval mechanism with data transformation and ingestion, enhancing the capability to extract extensive log volumes from the Netskope Tenant to the Netskope Cloud Exchange platform. Optimized the performance of the platform by remarkable 50% increase in throughput while reducing RAM usage by 2x. Built a circuit breaker mechanism to ensure stable data ingestion under heavy loads, improving system reliability and reducing downtime. Developed Netskope IoT module to transfer the high volume of assets data from 3rd party platforms to the Netskope Device Intelligence platform with supported transformation. Managed Python async tasks using Celery and RabbitMQ broker. HRMS - Internal Tool: Handled a management portal in Python, Flask, PostgreSQL, Docker. Collaborated with cross-functional teams to deliver critical enhancements and bug-fixes. Redesigned an existing feature using hashing with reduced time-complexity of O(1), at the expense of extra space. Netskope AI plugin Automated common query tasks by implementing a Netskope AI plugin with Amazon Bedrock, enhancing organizational efficiency by enabling rapid, streamlined access to Alerts and Events data within the Netskope Tenant. Developed an AI agent that intelligently redirected queries to appropriate tools, facilitating data extraction from platforms such as Netskope, Crowdstrike, and Okta. Integrated documentation support by enabling the chatbot to answer queries related to Netskope Cloud Exchange, providing users with quick access to relevant information. Machine Learning Engineer Intern Sanatan Tech Innovations, Ahmedabad, India • Jan 2022 - Feb 2025 Aug 2021 - Nov 2021 Developed an algorithm using the YoloV5 model that can accurately count the number of individuals crossing a user-specified boundary within a UI. Used light weight python framework Flask for the backend. H ACKATHONS ML Based Compliance Application and Chatbot Gemini Ultra Hackathon • Developed an AI-powered compliance application using Gemini Pro, automating artifact gathering and enhancing security through asset patch level and Windows OS assessments. Integrated a chatbot interface to provide real-time support to IT administrators during audits, earning recognition as the third-best solution in the Gemini Ultra 1.0 hackathon by lablab.ai P ERSONAL P ROJECTS Data Cleaning and Querying Engine Github • This project leverages advanced Large Language Models (LLMs) and supporting frameworks - Langchain Pandas Agent to clean, transform, and analyze flight booking datasets. The goal is to empower users to handle inconsistencies, fill missing values, rename columns for business-friendly querying, and perform data-driven analysis through an intuitive interface. Chatbot for API Documentations Github • Integrated Notion APIs to extract data from Notion pages in markdown format and efficiently saved it into text files for further processing. • Processed and indexed large datasets by creating chunks using MarkdownHeaderTextSplitter and RecursiveCharacterTextSplitter, generated embeddings with Cohere’s embed-english-v3.0 model, and stored them in ChromaDB. • Implemented a Reliable RAG (Retrieval-Augmented Generation) pipeline by leveraging LLMs to validate context relevance of data retrieved from the vector database, ensuring output groundedness, and detecting hallucinations in LLM-generated responses. EDUCATION L. D. College of Engineering Bachelor of Engineering in Computer Engineering • Graduated with a distinguished CGPA of 8.6. Ahmedabad, Gujarat, India June 2018 - June 2022
Get your freelancer profile up and running. View the step by step guide to set up a freelancer profile so you can land your dream job.