Senior Data Engineer: Agentic AI & GCP Pipelines

Vibehackers; Hinoba-an; On-site; PHP 1,800,000 - 2,400,000; Full time

Job summary

Vibehackers in the Philippines seeks a Senior Data Engineer to design, build, and operate production-grade batch and streaming data pipelines on Google Cloud Platform while integrating agentic AI capabilities to enable autonomous workflows.

You will work with LangChain, LlamaIndex, and other LLM frameworks to embed AI reasoning into data platforms, collaborating with cross-functional teams to scale data infrastructure on GCP.

Qualifications

• 8+ years of experience in data engineering or platform engineering roles.
• Strong proficiency in Python and Java.
• Experience with Spring Boot, dbt, and Apache Spark.
• Hands-on experience with Google Cloud Platform (GCP).
• Proven experience building production-grade batch and streaming data pipelines.
• Strong understanding of distributed data systems and analytical platforms.
• Solid understanding of agentic AI principles: autonomous agents/workflows, tool calling, memory, and LLM-based reasoning in production.
• Experience with LLM frameworks (LangChain, LlamaIndex, or custom agent frameworks).
• Familiarity with prompt engineering, retrieval-augmented generation (RAG), and embeddings.

Responsibilities

• Design and implement production-grade batch and streaming data pipelines.
• Build and operate distributed data systems and analytical platforms.
• Integrate LLM frameworks and agentic AI concepts into production systems.
• Collaborate with platform and engineering teams to deploy and scale data infrastructure on GCP.

Skills

Python

Java

Distributed systems

Batch processing

Streaming data

Spark

GCP

LangChain

LlamaIndex

LLM concepts

Tools

Spring Boot

dbt

Google Cloud Platform

Job description

Vibehackers in the Philippines seeks a Senior Data Engineer to design, build, and operate production-grade batch and streaming data pipelines on Google Cloud Platform while integrating agentic AI capabilities to enable autonomous workflows.

You will work with LangChain, LlamaIndex, and other LLM frameworks to embed AI reasoning into data platforms, collaborating with cross-functional teams to scale data infrastructure on GCP.