Data Engineer

Role

Job location

About Us

At I, Saras, we develop AI applications for students, teachers and professionals.

Why you should apply for I, Saras?

• Work in emerging tech like AI, ML and NLP.
• Funded by Startup India Scheme for being an innovative startup.
• Incubated at IIM Lucknow.

Role Overview

Build and maintain data infrastructure for AI-powered educational applications, enabling seamless data flow and intelligent features for students and teachers.

Key Responsibilities

Technical Documentation

• Understand business requirements from product docs (PRD and FSD)
• Translate them into Technical Specification Documents (TSD)
• Create comprehensive data architecture documentation
• Define data schemas (protobuf) and API specifications (OpenAPI)

DataOps & Pipeline Engineering

• Design and implement ETL/ELT pipelines for data processing
• Build scalable data ingestion and transformation workflows
• Extract structured data from unstructured sources (html, pdf, docx)
• Manage data pipeline orchestration and monitoring
• Ensure data quality, validation, and cleaning processes

Data Collection & Processing

• Implement web scraping solutions using Scrapy and other tools
• Build automated data collection systems

Search & AI Infrastructure

• Develop and optimize search and ranking algorithms
• Build RAG (Retrieval-Augmented Generation) pipelines for LLM applications
• Implement and manage vector databases for similarity search
• Design recommendation systems for educational content

Cross-functional Collaboration

• Work with Product and Engineering teams on data requirements
• Support ML/AI teams with clean, processed datasets

Required Qualifications

• 4+ years of experience in data engineering or data science
• Proficiency in Python, SQL, NoSQL and data processing frameworks
• Experience with ETL/ELT tools and pipeline orchestration

Technical Skills

• Languages: Python, SQL, Shell scripting
• Frameworks: Scrapy, Pandas, Apache Airflow, dbt
• Databases: PostgreSQL, MongoDB, Vector DBs (Pinecone)
• Cloud: AWS/GCP data services, Docker
• Tools: Git, CI/CD, monitoring and logging systems

What We Offer:

• Opportunity to shape the future of AI in education
• Competitive salary and benefits.
• Continuous learning and development opportunities.

We are an equal opportunity company and value diversity. We do not discriminate on the basis of religion, caste, language, race, color, region, gender, sexual orientation, age, marital status or disability status.