Senior Data Engineer

career international - fos pte. ltd.; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

Career International - FOS Pte Ltd invites a seasoned production engineer to join our team in Singapore. The role focuses on data ingestion from multiple sources, document parsing of complex bilingual materials, and building scalable data pipelines.

You will design data warehouses and manage ETL using modern orchestration tools, while deploying LLM-based services via OpenAI/Anthropic APIs, all within a cloud-first environment.

Qualifications

• 5–10 years of production engineering experience building online systems.
• Strong Python and SQL skills; data modeling, testing, and performance tuning.
• Hands-on experience parsing real-world messy documents (PDF, HTML, XBRL).
• 2–3 years of production LLM application experience, with deployment track record.
• Familiarity with at least one orchestration framework (Airflow / Prefect / Dagster).
• Experience with schema design in at least one modern cloud data warehouse.
• Strong communication skills; professional English proficiency.

Responsibilities

• Data ingestion: Multi-source scraping and integration, stable and schedulable.
• Document parsing: Structured extraction from PDF / HTML / XBRL, including bilingual docs.
• Data warehouse design & implementation using Snowflake / BigQuery / Postgres.
• Pipeline orchestration & monitoring: ETL with Airflow / Prefect / Dagster, with data quality checks, alerts, and lineage tracking.
• LLM application layer: Use of OpenAI / Anthropic APIs + open-source models.
• Structured outputs, retrieval-augmented generation.
• Basic evaluation and quality monitoring.
• Backend services: Query APIs via FastAPI, serving downstream analyst tools.
• Cloud infrastructure: GCP / AWS, leveraging managed services to minimize operational burden.

Skills

Python

SQL

Data modeling

Testing

Performance tuning

Document parsing

LLM applications

Orchestration

Data warehouse design

Communication

English proficiency

Tools

Airflow

Prefect

Dagster

Snowflake

BigQuery

Postgres

FastAPI

dbt

Neo4j

OpenAI API

Job description

Location/Office:Raffles Quay

Working hours:Mon-Fri, 9am-6pm (Hybrid)

Compensation:Basic Salary + Performance bonus

Responsibilities

• Data ingestion: Multi-source scraping and integration, stable and schedulable
• Document parsing: Structured extraction from PDF / HTML / XBRL formats, including image-based PDFs, complex tables, and bilingual (Chinese/English) documents
• Data warehouse design & implementation: Schema design and maintenance using modern cloud warehouses (Snowflake / BigQuery / Postgres)
• Pipeline orchestration & monitoring: Production-grade ETL on Airflow / Prefect / Dagster, with data quality checks, alerts, and lineage tracking
• LLM application layer:
• Use of OpenAI / Anthropic APIs + open-source models
• Structured outputs, retrieval-augmented generation
• Basic evaluation and quality monitoring
• Backend services: Query APIs via FastAPI, serving downstream analyst tools
• Cloud infrastructure: GCP / AWS, leveraging managed services to minimize operational burden

Requirements

• At least 5–10 years of production engineering experience, having built complete online system.
• Strong Python and SQL skills; experience in data modeling, testing, and performance tuning
• Hands-on experience parsing real-world messy documents (PDF, HTML, XBRL)
• 2–3 years of production LLM application experience, with deployment track record
• Familiarity with at least one orchestration framework (Airflow / Prefect / Dagster)
• Experience with schema design in at least one modern cloud data warehouse
• Strongly preferred: founding engineer experience, building end-to-end data systems in early AI startups
• Strong communication skills for direct collaboration with research and founding teams
• Professional working proficiency in English

Nice-to-Have

• Experience building data infrastructure supporting NLP / LLM workloads
• Hands-on dbt experience
• Multi-tenant / access control design experience
• Introductory knowledge of graph databases (Neo4j)

We regret only shortlisted candidates will be notified. Important Note: Career International - FOS Pte Ltd is committed to safeguarding your personal data in accordance with the Personal Data Protection Act (PDPA). Please read our privacy statement on our corporate website https://www.careerintlinc.com/southeast-asia/