status: available for full-time roles

Prateek Kumar

Software Engineer · GenAI · Data Engineering

I build Generative AI applications, data pipelines, and backend services — from production RAG systems to ETL workflows that keep data reliable at scale.

Data & GenAI Engineer @ Nexturn · Databricks Certified · Bengaluru, India

Hire Me Download Resume View Projects →

baseBengaluru, IN

roleData & GenAI Engineer

eduNIT Srinagar '25

certDatabricks GenAI Assoc.

/about

From debugging circuits to building GenAI pipelines.

I studied Electronics & Communication Engineering at NIT Srinagar, but found myself drawn to software long before graduation. Late nights on LeetCode — 500+ DSA problems solved — and a final-year stint at Nexturn that turned into a full-time offer the day I graduated.

Today I work as a Data & GenAI Engineer, splitting my time between two disciplines most teams keep separate: data engineering (SQL, ETL pipelines, PySpark, Spark, Airflow) and applied Generative AI (LangChain, FAISS, RAG, OpenAI APIs). I also hold a Databricks Certified Generative AI Engineer Associate credential.

The problems I find most interesting sit at the intersection — making retrieval accurate enough to trust, building pipelines that don't drift silently, and writing APIs that hold up when users actually show up. I'd rather ship something reliable than something flashy.

Backend & Data

REST APIs, SQL, ETL pipelines with PySpark, Spark, and Airflow

Applied GenAI

RAG systems, vector search with FAISS, LLM application engineering

/experience

Where I've worked.

Data & GenAI Engineer

Nexturn · Bengaluru, India

Sep 2024 — Present

Joined during my final year at NIT Srinagar; converted to full-time upon graduating in 2025.

Designed and built a Retrieval-Augmented Generation (RAG) application using LangChain and FAISS for domain-specific question answering over unstructured documents.
Engineered the full document processing pipeline end-to-end — chunking, embedding generation, vector indexing, and retrieval — for multi-turn conversational queries.
Integrated OpenAI APIs and iteratively refined prompt templates through repeated testing to improve response relevance for domain-specific queries.
Developed and optimized SQL queries using joins, aggregations, CTEs, and window functions for data transformation and business reporting.
Built and debugged ETL pipelines to ingest, clean, and transform structured datasets using Spark.

Python LangChain FAISS OpenAI API Spark SQL

/projects

Things I've built.

RAG-Based Document Q&A System

Associated with Nexturn

An end-to-end RAG application that lets users ask natural language questions over their own documents and receive context-grounded answers. Handles document ingestion, chunking with LangChain, embedding generation with Sentence Transformers, vector retrieval via FAISS, and LLM response generation — all through an interactive Streamlit interface.

Python LangChain FAISS Sentence Transformers OpenAI API Streamlit

Expedia — Data Engineering Project

client project

Onboarded to Expedia's data engineering team, gaining hands-on familiarity with the team's ETL pipelines and data workflows. Set up the development environment and explored the project's data processing architecture through knowledge-transfer sessions and technical documentation. Currently building practical experience with PySpark, Apache Spark, SQL, and Airflow.

Python PySpark Apache Spark SQL Airflow

ServiceNow SecOps — Exploitable Likelihood Score Dashboard

Security Use Case

A vulnerability-prioritization tool that computes an Exploitable Likelihood Score (ELS) from CVSS and threat data, backed by a custom ServiceNow table managing the underlying application data. Developed UI Builder pages to visualize ELS scores, vulnerability groupings, and Security Incident (SIR) records for security analysts.

ServiceNow UI Builder JavaScript

ITSM — ServiceNow to Salesforce Data Migration

internal project

Performed functional testing of the ServiceNow-to-Salesforce data migration workflow, validating field mappings, transformed data, and migration results. Compared source and target data across PostgreSQL tables to identify discrepancies and reported migration issues for resolution.

ServiceNow Salesforce PostgreSQL Data Migration Testing

/skills

What I work with.

Languages

Python JavaScript SQL

Backend & APIs

REST APIs Node.js Express.js OOP DSA

Data Engineering

PySpark Apache Spark Apache Airflow ETL Pipelines Data Transformation

Generative AI

LangChain FAISS RAG Vector Embeddings Semantic Search Prompt Engineering OpenAI API

Databases

PostgreSQL MongoDB Query Optimization

Tools & Platforms

Git GitHub Linux Databricks

/achievements

Track record.

DSA problems solved on LeetCode

Year of production engineering experience

Projects shipped across GenAI, data, and SecOps domains

Databricks GenAI certification earned

Databricks Certified Generative AI Engineer Associate

Industry certification validating expertise in designing and building GenAI applications on the Databricks platform.

View Credential ↗

Certified

National Institute of Technology (NIT), Srinagar

B.Tech in Electronics & Communication Engineering

Coursework: Data Structures & Algorithms, DBMS, Operating Systems, OOP

2021 — 2025

/why-hire-me

What I bring to a team.

Production GenAI experience

Not just prototypes — I've built and maintained a RAG pipeline end-to-end, including the ingestion, retrieval, and prompt-iteration cycle that makes LLM answers reliable in production.

Data engineering fundamentals

Hands-on with PySpark, Spark, and Airflow for ETL. I understand how data actually moves and breaks at scale, and I'm currently building on this through the Expedia data engineering project.

Strong CS fundamentals

500+ solved problems on LeetCode and a B.Tech grounding in DSA, DBMS, and OS — the foundations that make debugging and system design faster.

Certified in Generative AI

Databricks Certified Generative AI Engineer Associate — a signal that my GenAI knowledge goes beyond tutorials and includes production-grade design patterns.

Backend & API development

Comfortable writing REST APIs with Node.js and Express.js, optimizing SQL for reporting, and debugging data-intensive systems where correctness matters.

Fast ramp-up

Joined as an intern during my final year, shipped a production RAG system, and converted to a full-time engineer — I learn quickly and I ship.

/contact

Let's work together.

Open to full-time roles in software engineering, data engineering, and GenAI. I usually respond within 24–48 hours.

email kumarprateek1833@gmail.com phone +91 63918 37992

location Bengaluru, India

linkedin /in/prateek-kumar github /prateek1833 leetcode /Prateek_Kumar_24 resume Download PDF ↓