AI & Data Engineer

Azura Labs; Indonesia; On-site; IDR 120,000,000 - 240,000,000; Full time

Benefits offered by this job

Health insurance

Catering menus

Job summary

Azura Labs is building next‑generation intelligent systems. This role focuses on architecting agentic workflows that can reason, remember, and act, enabling autonomous decision making across data pipelines and applications.

You will design RAG pipelines, manage memory, and integrate MCP. Expect to work with Python, SQL, NLP models, and vector databases to deliver scalable AI capabilities—collaborating with data science and platform teams.

Qualifications

• 3–5 years of experience in related field.
• Experience with graph databases for RAG and knowledge graphs.
• DevOps/MLOps: Docker, Kubernetes, or CI/CD for AI services.
• JSON-RPC or MCP architecture familiarity.
• Knowledge of DBT.

Responsibilities

• AI & LLM Orchestration: design autonomous agents with multi-step reasoning.
• Data Engineering & ML: build scalable ETL/ELT, feature engineering, and data modeling.
• NLP: fine-tune NLP models for NER and intent classification.
• RAG pipelines: build and optimize retrieval augmented generation.

Tools

Python

FastAPI

Pydantic

Pandas

SciKit-Learn

PySpark

LangChain

LangGraph

MCP

Vector databases

Pinecone

Milvus

Weaviate

pgvector

PostgreSQL

Snowflake

BigQuery

Data Warehousing

Star/Snowflake schemas

ETL with Airflow

Hugging Face

BERT

NLP

DBT

Neo4j

Job description

In this role, you will contribute to the development of next-generation intelligent systems by architecting agentic workflows that can reason, remember, and act.

REQUIREMENTS

• Programming: Mastery of Python (FastAPI, Pydantic, Pandas, ScykitLeran, Pyspark).
• AI Frameworks: Hands‑on experience with LangChain, LangGraph, or similar libraries focused on agentic behavior. Understanding of MCP.
• Experience with Vector Databases (e.g., Pinecone, Milvus, Weaviate, or pgvector).
• Strong proficiency in Relational Databases (PostgreSQL / Snowflake / BigQuery).
• Data Warehousing: Clear understanding of Star/Snowflake schemas,Fact/Dimension modeling, and modern data stack principles.
• NLP: Proven experience with Hugging Face ecosystem, BERT-family models, andintent classification techniques.
• ETL: Able to create & maintain ETL jobs with Python & Airflow.

KEY RESPONSIBILITIES

1. AI & LLM Orchestration

• Agentic Systems: Design and implement autonomous agents capable of multi-step reasoning, planning, and tool use.
• State & Memory Management: Develop robust mechanisms for maintaining conversation context and long‑term memory in LLM workflows.
• MCP Integration: Implement the Model Context Protocol (MCP) to standardize how our AI models interact with external data sources, tools, and local environments.
• Retrieval Augmented Generation (RAG): Build and optimize RAG pipelines using vector databases to provide LLMs with relevant, real‑time context.

2. Data Engineering, Analytics & Machine Learning

• Analytical SQL: Write complex, high‑performance SQL for data analysis,transformation, and feature extraction.
• Data Modeling: Design and maintain Dimension and Fact tables within astructured Data Warehouse environment.
• Feature Engineering: Identify and extract key features from diverse datasets to improve model performance and business insights.
• Pipeline Development: Build scalable ETL/ELT processes that ensure data quality and availability for both AI models and BI tools.
• Ability to perform Exploratory Data Analysis (EDA) to inform model architecture.
• Supervised & Unsupervised Learning: Implement and evaluate models across the ML spectrum, from predictive regressions to discovery‑based clustering.
• Classification & Regression: Understanding of basic ML techniques to support data driven analytics.
• Recommendation Engines: Design and deploy recommendation systems(collaborative filtering, content‑based, or hybrid).
• Clustering: Use unsupervised techniques to identify patterns in dataset features and segment user behavior.

3. Natural Language Processing (NLP)

• Implement and fine‑tune NLP models for tasks such as Named Entity Recognition (NER) and Intent Translation.
• Work with transformer‑based architectures like BERT to enhance text understanding and classification within our product ecosystem.

PREFERRED QUALIFICATIONS

• 3–5 years of experience in related field
• Graph Databases: Experience with Neo4j or similar Graph DBs for advanced RAG(GraphRAG) and knowledge graph construction.
• DevOps/MLOps: Experience with Docker, Kubernetes, or CI/CD pipelines for AIservices.
• Protocol Knowledge: Deep familiarity with JSON‑RPC or the underlyingarchitecture of MCP.
• Knowledge of DBT.

Explore Our Benefits

We believe that anything can be realized. And we want to help you, make what you dream of come true. Become a part of our workforce!

We offer ongoing opportunities for your professional growth.

Health & Insurance

We provide employee health and employment insurance. We are committed to maintaining employee welfare, one of which is by providing catering menus for every employee.