Data Engineer - Đi Làm Ngay

· Data Pipeline Architecture: Design, build, and maintain scalable data pipelines to ingest, clean, and process massive volumes of real estate data from fragmented sources, including MLS feeds, public tax records, and real-time user clickstreams.

· Data Mining & Advanced Analytics: Apply pattern recognition, association analysis, and clustering algorithms to extract actionable intelligence from property data, identify market trends, and segment customer behaviors.

· Data Imputation & Quality Assurance: Build robust imputation models to automatically detect anomalies and estimate missing/erroneous data (e.g., missing bedroom counts or inaccurate square footage) from raw MLS feeds, ensuring high accuracy for downstream valuation algorithms.

· Data Modeling & Storage: Design optimal Data Lake/Data Warehouse architectures to effectively store and manage a hybrid of structured data (prices, geospatial coordinates) and unstructured data (3D tours, property images, and legal documents).

· Real-time Data Strategy: Implement data streaming architectures (utilizing tools like Apache Kafka or AWS Kinesis) to support real-time data processing, ensuring low-latency updates for AI inference and property listings.

· Data Governance & Compliance: Establish strict data quality standards, encryption, and access controls to ensure the infrastructure strictly complies with data privacy laws, FinCEN reporting rules, and fair housing regulations.

· AI & ML Development: Develop and deploy core PropTech machine learning models, including deep learning-based property valuation algorithms (AVMs) and Contextual Bandits for personalized user recommendations.

· Multi-Agent AI Integration: Architect a multi-agent AI system that acts as a central coordinator, routing user intents (via function and tool calling) across different domain-specific skills such as property search, financing, and tour scheduling.

· Agentic Coding Execution: Utilize advanced AI coding assistants and agentic IDEs to automate data transformation scripts, generate infrastructure-as-code, and accelerate the prototyping of machine learning models.

● Minimum 3 years of proven experience combining Data Engineering and Machine Learning/AI development.

● Experience developing PropTech products is a strong advantage.

● Bachelor's or Master's degree in Computer Science, Data Science, Mathematics, or a related technical discipline. 

● Strong programming proficiency in Python and SQL for complex data manipulation and model development. 

● Hands-on experience building data pipelines using cloud-based big data technologies (AWS, GCP, or Azure) and streaming platforms. 

● Practical experience in training and deploying machine learning models using frameworks such as TensorFlow, PyTorch, or Scikit-learn. 

● Proven ability to utilize Agentic Coding tools and workflows (AI-assisted IDEs, multi-agent parallel workspaces) to delegate tasks to AI and speed up software delivery. 

● Ability to analyze document business requirements, and create data flows and diagrams. 

● Skills in feature prioritization, and project management. 

● Proficiency with tools like Jira, Trello, Notion. 

● Excellent communication, persuasion, and teamwork skills. 

● Ability to work under pressure, multitask, and adapt in a fast-paced start-up environment.

- Salary: competitive 

- Working time: 5 days/week (Monday to Friday) 

- Performance Bonuses: Quarterly and annual bonuses based on KPIs - Comprehensive Insurance: Premium health insurance for you and your family 

- Leave Policy: 14 days of annual leave + public holidays as per regulations 

- Professional Development: Annual budget for training, workshops, and certifications. 

- Work Environment: Modern office in the heart of District 2, Ho Chi Minh City, with a flexible hybrid work model. 

- Work-Life Balance: Wellness programs for physical and mental health, team-building activities. Interview Process 

- Submit CV, Project Portfolio, and Cover Letter to [email]. - Initial interview with HR (15 minutes). 

- Round 1: Technical discussion with Product Manager (1-2 hours).

- Round 2: Presentation of technology vision and strategy to CEO and senior leadership. 

- Final evaluation and offer discussion.