Senior AI Engineer – Search & Retrieval

About the role

Join intive’s global team of 2,000 professionals to design, build, and optimise large‑scale search and retrieval platforms. You will work with cutting‑edge AI technologies to deliver fast, reliable, and semantic search experiences for leading brands.

Key responsibilities

• Design, develop and optimise backend services and APIs using Python (FastAPI or Flask).
• Build and maintain ETL and data ingestion pipelines, including asynchronous and event‑driven workflows.
• Implement semantic, vector, KNN, and Retrieval‑Augmented Generation (RAG) solutions.
• Manage OpenSearch/Elasticsearch clusters, mappings, sharding, and performance tuning.
• Develop scalable backend components in Node.js/TypeScript.
• Deploy, operate, and troubleshoot cloud‑native solutions on AWS.
• Monitor, debug and optimise production systems for reliability and scalability.

Required profile

• 8+ years of backend engineering experience building distributed, high‑performance systems.
• Strong hands‑on experience with Python for backend services and data pipelines.
• Proven expertise with FastAPI or Flask and mixed Python/Node.js‑TypeScript ecosystems.
• Deep knowledge of OpenSearch/Elasticsearch architecture and query DSL.
• Experience implementing semantic search, embeddings, vector search and RAG frameworks such as LlamaIndex.
• Solid AWS experience (Lambda, ECS, Managed OpenSearch, ALB/NLB) and event‑driven messaging (SQS, Kafka, SNS, RabbitMQ).

Required skills

• Python
• FastAPI
• Flask
• Node.js
• TypeScript
• OpenSearch
• Elasticsearch
• LlamaIndex (or similar RAG framework)
• AWS (Lambda, ECS, Managed OpenSearch, ALB, NLB)
• SQS, Kafka, SNS, RabbitMQ
• Unit testing frameworks for Python and JavaScript/TypeScript