Portrait of Abhishek Kumar Prasad

AI/ML Data Engineering

I build the pipelines
behind trustworthy AI.

4+ years building scalable data pipelines and RAG-based LLM solutions on Azure, Snowflake and Databricks. Now studying M.Sc. Data Science in Marburg.

Open to working student roles (20 hrs/week) in AI/ML or Data Engineering in Hesse

See my work Get in touch
0+

years in data engineering

0

professional roles

0

countries: Nepal, India, Germany

0

languages spoken

My journey

Click a card to see what I built.

AI/ML Data Engineer

FinPlusTech Inc. · Kathmandu (Remote), Nepal

Sep 2022 – Sep 2025
Regulatory docs→Chunk + embed→Vector index→RAG chatbot
  • RiskAI: core contributor to an AI compliance platform aligned with the EU AI Act, including a RAG chatbot for semantic search across regulatory documents.
  • Pipelines: designed and optimized ETL/ELT with Azure Data Factory, Airbyte, Spark, Databricks and Logic Apps.
  • Retrieval: built document workflows (chunking, summarization, embeddings, vector indexing) for hybrid search over structured and unstructured data.
  • Warehousing: Snowflake optimization and PostgreSQL schema design for better query performance and cost.
  • Dashboards: Power BI and Kibana for financial reporting and model performance tracking.
LangChainFAISSChromaDBDatabricksSnowflakeAzure Data FactoryAirbyte

Data Engineer

Rosebay Corporate · Kathmandu, Nepal

May 2021 – Aug 2022
Multiple sources→SSIS / SQL ETL→Data lake + warehouse→Power BI
  • Designed and maintained enterprise data warehouses on Microsoft SQL Server.
  • Built and scheduled ETL workflows with SSIS and SQL to automate integration from multiple sources.
  • Maintained a single source of truth on Azure Data Lake.
  • Created Power BI dashboards for internal reporting, plus analytics reports in Databricks (Python, Spark).
SQL ServerSSISAzure Data LakePower BISpark

Data Science Intern

The Spark Foundation · Bengaluru, India

Apr – May 2021
  • Data wrangling, analysis and visualization in Python.
  • Tested and evaluated machine learning models.
PythonMachine Learning

Skills

What I work with, grouped by what it's for.

Data Engineering

SparkDatabricksDelta Live TablesSnowflakePostgreSQLSQL ServerETL / ELTData ModelingBig Data Analytics

AI / ML

RAGLLMsGenerative AIAgentic AILangChainFAISSChromaDBMachine LearningScikit-learn

Programming & Databases

PythonSQLNoSQLMongoDBGit

Cloud & BI

Azure Data FactoryAzure Data LakeAirbyteLogic AppsPower BIKibanaExcel

Languages

Nepali native
Hindi native
English C1 – C2
German B1

Projects

Live demo

Age & Mood Detection

Webcam or photo in, estimated age and mood out. It runs entirely in your browser, so nothing is uploaded.

Computer Visionface-api.jsPretrained CNNs
Try it live →

RiskAI: EU AI Act Compliance

AI compliance platform with a RAG chatbot for semantic search across regulatory documents. I was a core contributor at FinPlusTech.

RAGLangChainFAISSChromaDB

SemEval 2026 Task 5: AmbiStory

Rating how plausible a word meaning is within a short story, using a fine-tuned RoBERTa regressor plus an NLI-based second stage.

RoBERTaDeBERTa NLIEnsembleHuggingFace
GitHub →

Enterprise Data Platform

SQL Server warehouse and Azure Data Lake single source of truth, fed by scheduled SSIS pipelines and served through Power BI. Built at Rosebay Corporate.

SQL ServerSSISAzure Data LakePower BI

Education

In progress

M.Sc. Data Science

Philipps-Universität Marburg · Germany

Oct 2025 – present

NLPData IntegrationStatistics

B.Tech Computer Science & Engineering

Reva University · Bengaluru, India

Aug 2016 – Jun 2020

Let's talk

Looking for a working student role (20 hrs/week) in AI/ML or Data Engineering in Hesse. Also happy to talk about RAG, pipelines or NLP.

Email LinkedIn GitHub