Senior AI Engineer - Agentic RAG & Data Pipelines

Luxoft Singapore; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

Luxoft Singapore seeks AI Engineers to design, develop, and maintain full-stack Python apps for trading surveillance initiatives. You will optimize AI systems and ensure scalable data management across environments.

You will build RAG systems, vector stores and data pipelines, and implement CI/CD for AI applications, using Snowflake/BigQuery/Databricks, and streaming technologies like Kafka and Spark.

Qualifications

• Minimum of 6 to 9 years of experience in AI/ML solution implementation.
• Minimum of 3 years of experience in Data Engineering (data pipelines, ETL/ELT, data warehousing, batch/streaming processing)

Responsibilities

• Design, develop, and maintain full-stack Python applications with modern frontend frameworks
• Build and optimize RAG (Retrieval-Augmented Generation) systems for AI applications
• Create and implement efficient vector databases and knowledge stores
• Develop APIs that connect frontend interfaces with backend AI services
• Implement and maintain CI/CD pipelines for AI applications
• Monitor application performance and troubleshoot issues in production
• Design and maintain data pipelines, ETL/ELT workflows, and data infrastructure to support AI and analytics workloads

Skills

Multi-Agent System Design

Full-stack AI Integration

Prompt Engineering

RAG Systems

AI Safety & Governance

Semantic Modeling

LLMOps

ETL/ELT

Data Warehousing

Batch/Streaming

Data Modeling

SQL proficiency

Tools

Snowflake

BigQuery

Redshift

Databricks

Spark

Kafka

Flink

LangChain

LangGraph

Streamlit

Gradio

FastAPI

Job description

Luxoft Singapore seeks AI Engineers to design, develop, and maintain full-stack Python apps for trading surveillance initiatives. You will optimize AI systems and ensure scalable data management across environments.

You will build RAG systems, vector stores and data pipelines, and implement CI/CD for AI applications, using Snowflake/BigQuery/Databricks, and streaming technologies like Kafka and Spark.