AI Engineer

Job Overview

We are seeking an AI Engineer to design and scale robust enterprise Generative AI platforms enabling rapid creation and deployment of applications powered by large language models (LLMs) across the enterprise. This role involves building reusable infrastructure such as retrieval-augmented generation (RAG) pipelines, vector databases, model serving layers, and frameworks for orchestrating agent workflows.

Core Responsibilities

• Construct and sustain RAG pipelines and orchestration frameworks for LLMs.
• Develop reusable services and APIs tailored for Generative AI applications.
• Support multi-agent and agentic workflow capabilities for complex AI tasks.
• Implement scalable infrastructure for model serving leveraging tools such as vLLM and Triton, along with facilitating APIs.
• Administer vector database systems and embedding pipelines effectively.
• Enhance overall system efficiency focusing on performance tuning and cost optimizations of LLM operations.
• Provide modular building blocks to AI teams aiming to accelerate AI developments.
• Enable swift experimentation cycles and deployment of GenAI solutions.
• Collaborate closely with AI and ML teams to drive organization-wide adoption of Generative AI technologies.
• Stay current on new tools and frameworks emerging in the Generative AI landscape and promote best practices within LLM operations.

Qualifications and Requirements

• Academic background with a Bachelor’s, Master’s, or PhD in Computer Science, Mathematics, or a related domain.
• Demonstrated ongoing learning and professional growth in Artificial Intelligence, Machine Learning, and relevant domains including Aviation, Cargo handling, Ground Handling, Freight, and Food Solutions.
• Between 3 to 5 years of professional experience in AI engineering or backend system development.
• Strong proficiency with LLMs, RAG methodologies, embeddings, and relevant toolkits such as LangChain, LlamaIndex, CrewAI.
• Experience managing vector database technologies like FAISS or Pinecone.