Looking for a job

preetanshu shukla

@preetanshushukla

Results-driven AI Engineer and Senior Data Engineer with 7+ years of experience building production-grade GenAI systems and datapipeline.

India

Message

What I'm looking for

I am looking for a challenging role that fosters innovation and growth, where I can leverage my data and AI engineering skills to drive impactful business decisions.

Results-driven AI Engineer and Senior Data Engineer with 7+ years of experience building production-grade GenAI systems and

enterprise-scale data pipelines. Deep expertise in RAG, LLMs, LangChain, LangGraph, Agentic AI workflows, and vector

databases, combined with strong AWS cloud data engineering (Glue, Lambda, Redshift, S3, Step Functions) and PySpark/Scala

ETL pipelines. Proven track record of deploying multi-agent LLM systems, delivering $1M+ in annual cost savings, reducing

manual effort by 60-70%, and leading cross-functional engineering teams of 6+ across enterprise and fintech domains.

Experience

Work history, roles, and key accomplishments

Current

AI Enginner

Current

infosys

Feb 2025 - Present (1 year 5 months)

• Designed and deployed a production-grade RAG-based GenAI assistant using LangChain, FAISS, and OpenAI APIs for
natural-language querying of enterprise SOPs, runbooks, and incident data, reducing knowledge retrieval time by 60%.

LLM Lang Chain RAG MCP AWS Amazon SageMaker AWS Glue ETL Data Engineering Python 3 Open AI GPT Knowledge Vector Databases ChromaDB fastAPI Agentic AI AI Model Deployment ETL

Senior Data Engineer

DXC Technology

Feb 2023 - Feb 2025 (2 years)

As a Senior Data Engineer, I transformed raw data into actionable insights, leading to $1M annual savings. I developed a PySpark + AWS Glue ETL framework and managed a team to enhance data processing capabilities.

Python Pyspark AWS Glue Redshift AWS Lambda Data Modeling ETL Apache Airflow Data Lake

Data Engineer

SHL

May 2022 - Feb 2023 (9 months)

In my role as a Data Engineer, I created a generalized framework in Spark and Scala for report generation and developed parsers for JSON and XML, optimizing data processing with distributed computing.

Spark Scala ETL Data Lake Data Warehouse JSON XML AWS Glue Data Modeling Continuous Deployment

Data Engineer/Analyst

BIjak

Jul 2021 - May 2022 (10 months)

I developed a highly optimized recommendation engine using machine learning algorithms and created a data pipeline for the recommendation system, leveraging AWS technologies for deployment.

Machine Learning AWS Data Pipelines Data Warehouse Redshift Python Flask API Development Data Modeling Deep Learning

Software Developer - Data Projects

.LIX CAPITAL

Jul 2019 - Apr 2021 (1 year 9 months)

As a Software Developer, I managed end-to-end data for a new lending product, developed ETL pipelines, and implemented machine learning models for decision-making processes.