NLP Data Engineer

PROJECT

We are developing a mobile application that allows users to compare prices of the same products across different stores in the United States. Our app aims to provide consumers with real-time insights into product availability, pricing, and brand choices, helping them make more informed shopping decisions. We are currently expanding our efforts to enhance the quality of product metadata and automate data processing, utilizing cutting-edge technologies like Natural Language Processing (NLP) and machine learning.

To support our rapid growth, we are looking for a talented Data Engineer with a strong focus on Prompt Engineering to help us build and optimize automated systems that will improve data accuracy, reduce manual work, and ensure smooth integration of new data sources. Your work will be instrumental in ensuring that our users can confidently compare prices with accurate and complete product information.

SALARY

💵 B2B: 20 000 - 30 000 PLN net

RESPONSIBILITIES:

Primary Role: Develop and maintain prompt-engineering scripts and semi-automatic flagging/review systems to clean, validate, and standardize metadata for various product fields. 

Prompt Engineering & Scripts:

• Create and optimize prompts/scripts to automatically clean, categorize, and tag product metadata.
• Improve existing scripts for product types, sizes, tags, brands, and other metadata fields.

Data Cleanup & Standardization:

• Write scripts to handle data cleanup for brands, prices, sizes, and availability.
• Convert size values to numerical representations based on product type-specific rules.

Manual Review System:

• Develop systems for manual review of flagged items in the data warehouse (DW).
• Build review mechanisms for user-flagged issues and those identified by automated systems.

Data Integration & Deduplication:

• Ensure proper merging of products by identifying and consolidating duplicates using UPCs and metadata.

Product Grouping:

• Create scripts for identifying and grouping similar products based on size, color, scent, etc.

SKILLS & QUALIFICATIONS

✅ 3+ years of experience as a Data Engineer or in a similar role.

✅ Strong proficiency in Python (Mid/Senior level), R (Mid/Senior level), and experience with Java is a plus.

✅ Experience with NLP techniques, especially in prompt engineering for data automation.

✅ Proficient in designing and optimizing ETL pipelines and working with cloud data warehouses (e.g., Snowflake, BigQuery, Redshift).

✅ Familiarity with product metadata structures and experience working with large datasets in a commercial environment.

✅ Excellent problem-solving skills and attention to detail, especially in data validation and error handling.

✅ Strong communication skills to work effectively with cross-functional teams, including QA, backend developers, and product managers (English and Polish B2 + is a must).

✅ Experience with APIs, data integration, and handling multiple data sources.

BENEFITS

✅ 25 days of paid leave for B2B or contract services;

✅ Flexible working hours, with the option to work remotely or from the office;

✅ Private healthcare (Luxmed);

✅ Subsidy for insurance (Warta);

✅ MPCharity: a program where you can propose initiatives that you would like to support.

ABOUT US

We are a Katowice-based IT company with over 100 people on board—and one dog. We have greatly diversified our operations, and despite the pandemic, we’ve experienced the most growth in the past few years. Our work focuses on our own product, getzendo.io, collaboration with a client from the United States, and a software house division (providing IT services to external companies).

RECRUITMENT PROCESS

Step 1: A 45-minute interview with an HR representative (you will receive information about the project, and we will ask a few basic questions);

Step 2: Technical Interview (about 1-1.5h)

Step 3:  Final interview with Product Owner (1h)