Product Data Engineer (Python or Ruby)

Bulgaria
Fully Remote
Full Time

Who We Are

Yamasoft is a Bulgarian software company and a leading software solutions provider. With over 25 years of experience in the software industry, our team brings expertise in building high-performing teams and delivering top-notch software solutions. We focus on delivering high-quality software that aligns seamlessly with our customers’ objectives.

Description

We are building a team around a variety of apps for road trip planning as well as finding camping locations across North America. In addition, the team will focus on designing and implementing new connected home and connected vehicle apps from the ground.

As a Product Data Engineer, you will own the quality, depth and reach of our points of interest (POI) data, which is the core of every product. You will augment, clean, fix and expand that data using AI tooling: smart scraping and aggregation, new data source integrations, and evaluation tools that decide the best metadata to store and show for each place. You are also a strong software engineer who contributes across the product and data storage layers. You will have plenty of room to shape how the wider engineering organization adopts and scales AI.

Key Responsibilities

      • Design, build and maintain smart scraping and aggregation tools that use LLMs and other AI techniques to collect, extract and normalize POI data at scale.
      • Identify, evaluate and integrate new data sources (partner feeds, APIs, open datasets), including matching and de-duplicating against existing POI records.
      • Build pipelines and tools to clean, fix and enrich existing POI data, such as locations, hours, amenities, categories and closures.
      • Develop evaluation tools and scoring logic that measure data quality and determine the best metadata (names, descriptions, photos, attributes) to display for each POI when sources disagree.
      • Apply LLMs, embeddings and ML methods to entity resolution, classification, extraction and enrichment, balancing accuracy, cost and human review.
      • Build monitoring for data coverage, freshness and accuracy, and use it to prioritize data improvement work.
      • Manually investigate and correct data when necessary, while turning those learnings into automated fixes at scale.
      • Contribute to product features as a software engineer, including API features that serve POI data to consumer applications.
      • Design and improve data storage, schemas and indexing (relational, search and geospatial) to support data quality and performance.
      • Diagnose and fix data and software defects when discovered.
      • Use AI coding assistants and agentic tooling in day-to-day work, and help teammates do the same.
      • Contribute to AI scaling initiatives across the engineering organization by sharing tools, patterns and workflows, and evaluating new models and AI tools.

Qualifications

      • 4+ years of experience in a full-time software engineering or data engineering role
      • 3+ years of experience with ETL automation, data pipelines and integrating third-party data sources
      • Strong proficiency in Python or Ruby and the ability to ramp up quickly
      • Hands-on experience building web scrapers or crawlers, including dynamic content, rate limits and responsible scraping practices
      • Practical experience building with LLMs in production, including prompt design, structured extraction, evaluation and cost management
      • Experience with Amazon Web Services (AWS), SQL (ideally Postgres) and Elasticsearch
      • Experience with data quality techniques such as entity resolution, de-duplication and validation
      • Strong communication and interpersonal skills
      • Exceptional problem-solving skills and a proactive mindset
      • Self-motivated and able to work with periods of full autonomy in a remote work environment
      • Strong organization skills with the ability to prioritize tasks and deliver on time

Nice to Have

      • Experience working with geospatial, POI or places data
      • Experience building evaluation frameworks or human-in-the-loop review for AI or data quality
      • Machine learning, embeddings or vector search experience
      • Experience with agentic workflows and AI tooling such as agent frameworks or MCP

What we offer

      • 25 Days Paid Time Off
      • Additional Health Insurance
      • Multisport card
      • The opportunity to be among the very first team members
      • Excellent career development opportunities
      • Attractive remuneration package

If you are interested in this job offer, please send your CV in English.

Do not apply if you are not located in Bulgaria.

All CVs will be treated in strict confidentiality. Only shortlisted candidates will be contacted.