Pratyush Mohanty
Hyderabad
Summary
Data Engineer skilled in Google Cloud Platform, Apache Spark, and LLM systems. Proven ability to design and deploy end-to-end data solutions that enhance operational efficiency and drive innovation.
Overview
3
3
years of professional experience
Work History
Data Engineer
Micron
Hyderabad
08.2022 - Current
- Designed and deployed an end-to-end LLM-powered chatbot system leveraging a comprehensive suite of Google Cloud Platform (GCP) services.
- Built robust data pipelines using Apache Spark on Dataproc, with intermediate staging in Cloud Storage.
- Created vector embeddings using Vertex AI Embeddings API, integrated Gemini Pro and ChatGPT (OpenAI) for semantic understanding and response generation using RAG (Retrieval-Augmented Generation) architecture.
- Implemented Vertex AI Search and Conversation (AI Application) for semantic document search and domain-specific grounding.
- Used Vertex AI Agent Builder to orchestrate modular, multi-turn conversational agents integrated with enterprise data.
- Developed and deployed REST APIs on Kubernetes (GKE) to expose LLM services and chatbot workflows at scale.
- Built serverless microservices with Cloud Run and Cloud Functions to support event-driven tasks and backend automation.
- Orchestrated ML workflows with Vertex AI Pipelines for automating data preprocessing, embedding generation, and model inference.
- Developed interactive chatbot UIs using Streamlit, deployed via Cloud Run for real-time, scalable user interactions.
- Set up end-to-end CI/CD pipelines using:
Cloud Build for automated testing and deployment
Artifact Registry for container image packaging and versioning, tightly integrated with Cloud Build
Cloud Deploy for rollout management across environments (dev/staging/prod)
Secret Manager for secure handling of credentials and tokens - Automated background workflows using Cloud Scheduler, Pub/Sub, and Eventarc for trigger-based processing and messaging.
- Monitored service health and performance with Cloud Monitoring, Cloud Logging, and custom dashboards in Looker Studio.
- Designed and optimized analytical and transactional models in BigQuery, AlloyDB, PostgreSQL, and MSSQL, using partitioning, clustering, indexing, and query tuning.
- Developed LLM-powered data enrichment and analytics pipelines in Snowflake and Snowflake Cortex.
- Created flexible and reusable data ingestion and transformation pipelines using Apache NiFi for hybrid cloud/on-prem environments.
Education
Bachelor of Technology - Computer Science And Engineering
National Institute Of Technology, Rourkela
Rourkela05-2022
Skills
- Google Cloud Platform (GCP)
- Apache Spark
- LLM systems
- Database management
- Big data technologies
- Large Language Models (LLM) & RAG Architecture
- CI/CD (Cloud Build Artifact Registry Cloud Deploy)
- Kubernetes (GKE)
- Data Engineering & ETL
- Python
Affiliations
Actively participated in corporate volunteering initiatives and won awards in coding and tech competitions at organizational and inter-company levels.
Languages
Odia
First Language
English
Advanced (C1)
C1
Hindi
Intermediate (B1)
B1
Timeline
Data Engineer
Micron
08.2022 - Current
Bachelor of Technology - Computer Science And Engineering
National Institute Of Technology, Rourkela
Similar Profiles
Bhanu ThumpatiBhanu Thumpati
Firmware Engineer at MicronFirmware Engineer at Micron
Wan Lin YiWan Lin Yi
OMT QE IQC Engineer Lead at MicronOMT QE IQC Engineer Lead at Micron
Steven YangSteven Yang
Manufacturing Engineer at MicronManufacturing Engineer at Micron
Logesvaran KaliappanLogesvaran Kaliappan
Senior Manager at MicronSenior Manager at Micron
ARAVA ANANTHA RAOARAVA ANANTHA RAO
Information Security Manager at Tata Consultancy ServicesInformation Security Manager at Tata Consultancy Services