GCP Data Engineer

CDI Solutions; San Jose (CA); On-site; USD 140,000 - 190,000; Full time

Job summary

CDI Solutions in San Jose, CA is seeking a senior data engineer to design and implement data pipelines on Google Cloud Platform and GenAI initiatives. You will leverage BigQuery, Cloud Composer, Dataflow, and Pub/Sub to deliver scalable data solutions for large-scale data sets.

The role requires 12+ years in data or software engineering, strong SQL, Python or Java, and experience with GCP and LLM integrations.

Qualifications

• 8+ years of data engineering or software engineering experience, ideally with large-scale financial or transactional data.
• Strong SQL skills, with hands-on BigQuery (or equivalent modern data warehouse) experience
• Proficiency in Python and/or Java for pipeline development and automation
• Experience with GCP (BigQuery, Cloud Composer/Airflow, Dataflow, Pub/Sub, or equivalents)
• Hands-on experience building with LLMs — prompt engineering, function/tool calling, or RAG pipelines
• Understanding of ETL/ELT design, data modeling, and performance tuning at scale
• Excellent communication skills — able to translate ambiguous business asks into concrete technical specs (data or AI-based)
• Comfort working directly with non-technical stakeholders (ops, compliance, finance) and adapting quickly to their domain
• High tolerance for ambiguity, shifting priorities, and production firefighting

Responsibilities

• Translate business needs into scalable data pipelines on GCP and GenAI initiatives.
• Design, build, test, and maintain data pipelines using Python/Java and modern data warehouses.
• Collaborate with stakeholders to convert ambiguous requirements into concrete technical specs.
• Support non-technical teams (ops, compliance, finance) with data and AI deliverables.
• Ensure data quality, performance, and governance at scale.

Skills

SQL

BigQuery

Python

Java

GCP

GenAI

LLMs

ETL/ELT

Data modeling

Data warehouse

Tools

BigQuery

Cloud Composer/Airflow

Dataflow

Pub/Sub

Job description

One of my Client is Hiring for GCP Data Engineering & GenAI at San Jose , CA

Location: San Jose , CA

Type : Contract

Exp - 12+ Years

Job Description:

• 8+ years of data engineering or software engineering experience, ideally with large-scale financial or transactional data
• Strong SQL skills, with hands-on BigQuery (or equivalent modern data warehouse) experience
• Proficiency in Python and/or Java for pipeline development and automation
• Experience with GCP (BigQuery, Cloud Composer/Airflow, Dataflow, Pub/Sub, or equivalents)
• Hands-on experience building with LLMs — prompt engineering, function/tool calling, or RAG pipelines
• Understanding of ETL/ELT design, data modeling, and performance tuning at scale
• Excellent communication skills — able to translate ambiguous business asks into concrete technical specs (data or AI-based)
• Comfort working directly with non-technical stakeholders (ops, compliance, finance) and adapting quickly to their domain
• High tolerance for ambiguity, shifting priorities, and production firefighting

Preferred Qualifications

• Experience building with Claude, OpenAI, or similar LLM APIs in production or internal-tool contexts
• Familiarity with MCP (Model Context Protocol) — building or configuring MCP servers/skills that connect LLMs to internal tools
• Experience with vector databases and embedding-based search for RAG applications
• Experience with financial reconciliation logic (PDA/CASH/VDA/SDA-type matching, or equivalent)
• Prior exposure to AI adoption/usage analytics, cost monitoring, or slot/performance optimization at scale