Data Engineer
Summary
Data Engineer building scalable data pipelines for NLP and LLM applications using Python, Apache Spark, and vector databases at an AI product company.
About Us
AiLogic Neural Network Pvt Ltd is an AI-driven product company focused on building advanced language technology solutions, including machine translation, document intelligence, and large-scale NLP systems. We are looking for a highly motivated Data Engineer to join our growing AI team and contribute to the development of scalable data processing pipelines for NLP and LLM applications.
Roles & Responsibilities
- Design, develop, and maintain scalable data pipelines for processing large volumes of structured and unstructured data.
- Build document ingestion and processing workflows for PDFs, scanned documents, HTML pages, and other text sources.
- Implement OCR, PDF parsing, HTML parsing, and text extraction pipelines.
- Develop document chunking and preprocessing frameworks for NLP and LLM-based applications.
- Work with Hugging Face models and NLP libraries for text processing tasks.
- Create and optimize data transformation workflows using Python, Apache Spark, and Spark SQL.
- Develop and manage Vector Database pipelines for embedding storage and retrieval.
- Implement text normalization, sentence segmentation, deduplication, and data quality processes.
- Design and implement data masking, classification, and categorization solutions.
- Collaborate with AI/ML engineers to prepare datasets for model training and inference.
- Optimize large-scale data processing workflows for performance, scalability, and cost efficiency.
- Maintain CI/CD pipelines and follow software engineering best practices.
- Monitor, troubleshoot, and improve production data processing systems.
Mandatory Skills
- Strong experience with Python programming.
- Hands-on experience in NLP concepts such as:
- Tokenization
- Text Processing
- Hugging Face Transformers
- Experience in:
- PDF Parsing
- OCR
- HTML Parsing
- Text Extraction
- Document Chunking
- Experience with Apache Spark and Spark SQL.
- Working knowledge of Vector Databases.
- Good understanding of Git and CI/CD practices.
- Experience building data pipelines and ETL workflows.
- Strong debugging and problem-solving skills.
Preferred Skills
- Text Normalization
- Sentence Segmentation
- Exact Deduplication and Near Deduplication
- Data Masking
- Data Classification & Categorization
- Embedding Generation and Retrieval Pipelines
- Large-scale Document Processing Systems
- RAG (Retrieval-Augmented Generation) Pipelines
Performance Optimization Skills
- CPU Distribution and Parallel Processing
- Pre-batch Generation Techniques
- Chunking Optimization Strategies
- Stream Processing vs Batch Processing
- GPU and CPU Parallel Distribution
- CUDA Optimization
- PyTorch Performance Tuning
- Spark Performance Optimization
Qualifications
- Bachelor's or Master's degree in Computer Science, Data Science, Information Technology, or a related field.
- 2–3 years of experience in Data Engineering, NLP Engineering, or AI Data Processing.
- Experience working with large-scale datasets and distributed computing frameworks.