Skip to content
Portrait of Akash Kumar Jha in a navy suit and burgundy tie

Hello, my name is

AkashKumar Jha.

Generative AI Engineer / LLM & RAG Developer

Building intelligence as a Generative AI Engineer, Machine Learning Engineer, Data Scientist, LLM & RAG Developer, AI Application Developer

I build intelligent applications that combine machine learning, large language models, and modern software engineering to solve real-world problems.

Portrait of Akash Kumar Jha in a navy suit and burgundy tie

Akash Kumar Jha

Generative AI Engineer

Noida, IN

01About Me

Turning Complex AI Ideas into Real-World Applications.

I'm an entry-level Generative AI Engineer and Python developer who enjoys taking AI ideas all the way from prototype to deployed product. My focus is Large Language Model applications and Retrieval-Augmented Generation: document processing, embedding pipelines, semantic search, and grounded question answering with source citations.

My flagship project, Akarika, is a production-deployed multilingual document assistant with 20-language support, page-level citations and voice interaction. Beyond GenAI, I bring a foundation in machine learning, NLP and data science, from data cleaning and exploratory analysis during my Data Science & Analytics internship at Zidio Development to building predictive models with Scikit-learn.

I also build the software around the models, including REST APIs, SQL databases and Next.js interfaces, so AI features reach people as real, usable applications.

Name
Akash Kumar Jha
Focus
Generative AI · LLMs · RAG · ML
Location
Noida, Uttar Pradesh, India
Studying
Bachelor of Computer Applications (BCA)

02Expertise

What I build

From retrieval pipelines to predictive models: the areas I work across, grounded in the tools on my resume.

Work with me
  • 01

    Generative AI Development

    RAG applications, LLM integrations, prompt engineering and intelligent AI workflows built with LangChain, the OpenAI API and Hugging Face.

    • #LLMs
    • #LangChain
    • #Prompting
  • 02

    Machine Learning

    Predictive modelling with classification, regression and clustering, backed by feature engineering and careful model evaluation.

    • #Scikit-learn
    • #TensorFlow
  • 03

    Data Science & Analytics

    Data cleaning and preprocessing, exploratory data analysis, statistical analysis and clear visual storytelling.

    • #Pandas
    • #SQL
    • #PowerBI
  • 04

    Natural Language Processing

    Text preprocessing, tokenisation, embeddings, semantic search, multilingual NLP, and speech-to-text / text-to-speech.

    • #Embeddings
    • #Multilingual
  • 05

    AI Application Development

    Shipping AI features as real products, combining Python, REST APIs, databases and modern Next.js front ends, deployed on Vercel.

    • #Python
    • #RESTAPIs
    • #Next.js
  • 06

    LLM & RAG Engineering

    Document ingestion, chunking, embedding pipelines, vector databases, context retrieval and grounded answers with source citations.

    • #VectorDBs
    • #Retrieval
    • #Citations
    See it in Akarika
Live projects
03
Languages in Akarika
20
Internship
01
Certifications
03

03Technical Skills

The toolkit behind the work.

Grouped by discipline. No made-up proficiency bars, just the languages, libraries and platforms I actually use.

  • Generative AI & LLMs

    08
    • Large Language Models
    • Retrieval-Augmented Generation
    • LangChain
    • OpenAI API
    • Hugging Face
    • Transformers
    • Prompt Engineering
    • LLM Application Development
  • RAG & Information Retrieval

    08
    • Text Embeddings
    • Vector Databases
    • Semantic Search
    • Vector Similarity Search
    • Document Chunking
    • PDF Text Extraction
    • Grounded QA
    • Source Citations
  • Machine Learning & NLP

    12
    • Scikit-learn
    • TensorFlow
    • Natural Language Processing
    • Multilingual NLP
    • Tokenization
    • Speech-to-Text
    • Text-to-Speech
    • Classification
    • Regression
    • Clustering
    • Feature Engineering
    • Model Evaluation
  • Programming

    05
    • Python
    • SQL
    • JavaScript
    • TypeScript
    • C++
  • Data Science

    07
    • Pandas
    • NumPy
    • Matplotlib
    • Seaborn
    • Power BI
    • Jupyter Notebook
    • Google Colab
  • Web Development & Databases

    05
    • Next.js
    • REST APIs
    • MySQL
    • PostgreSQL
    • MongoDB
  • Development Tools

    04
    • Git
    • GitHub
    • Vercel
    • Pygame

04Projects

Selected Projects

Exploring the intersection of artificial intelligence, data, and software engineering. Every project is live; click a card to open it.

View GitHub (opens in a new tab)

Showing 3 projects in All Projects.

  • Flagship

    Generative AI / LLM Engineering

    Akarika

    Multilingual RAG Document Assistant

    rag-pdf-nine.vercel.app(opens Akarika in a new tab)

    An end-to-end Retrieval-Augmented Generation app: upload PDFs, ask questions in natural language, and get answers grounded in the document with page-level citations, in 20 languages, by text or voice.

    Pipeline: PDF text extraction → Document chunking → Embedding generation → Vector storage → Semantic similarity search → Grounded answer + citations

    • Python
    • LLMs
    • RAG
    • Embeddings
    • Vector Database
    • Semantic Search
    • Next.js
    • Vercel

05Experience

Professional Experience

  1. –

    Internship

    Remote

    Data Science & Analytics Intern

    Zidio Development

    • Cleaned, transformed and preprocessed real-world datasets with Python, Pandas, NumPy and SQL, handling missing values, outliers and inconsistent records.
    • Carried out exploratory data analysis (EDA) and statistical analysis to surface patterns and actionable insights in the data.
    • Engineered features and developed predictive machine learning models with Scikit-learn, evaluating them with standard metrics.
    • Communicated findings through dashboards and visualisations built in Power BI, Matplotlib and Seaborn.
    • Python
    • Pandas
    • NumPy
    • SQL
    • Scikit-learn
    • Power BI
    • Matplotlib
    • Seaborn

06Education

Academic Foundation

  1. 2024 – 2027

    Bachelor of Computer Applications (BCA)

    Dr. Babasaheb Bhimrao Ambedkar Bihar University

    Muzaffarpur, Bihar

    Pursuing · 6th Semester
  2. 2022 – 2024

    Senior Secondary (Class XII) – CBSE

    Best Model Public School

    Hajipur, Bihar

    87%score
  3. 2022

    Secondary (Class X) – CBSE

    Mahua, Hajipur, Bihar

    95%score

07Certifications

Courses & Certifications

  • Generative AI

    Tutedude

    Completed
    Aug 2026
    Credential ID
    TD-AKAS-GA-1050
  • SQL for Data Analysis

    LinkedIn Learning

    Completed
    Mar 2026
  • Basics of Python (CR641)

    Cambridge International, UK

08Contact

Let's Build Something Intelligent Together.

Have an idea, opportunity, or collaboration in mind? I'd love to connect.

This form opens your email app with the message pre-filled. Nothing is sent until you press Send there.