AI GEO Engineer (Generative Engine Optimization)

Role Overview

A top-tier, corporate retail financial services institution is seeking a highly motivated and technically sharp AI GEO Engineer to join its newly formed Intelligent Automation and Research division. This role is strictly tailored for early-career professionals with 1 to 4 years of dedicated experience operating at the intersection of Natural Language Processing, data science pipelines, and conversational AI deployment. You will be responsible for building, optimizing, and evaluating architectures for Generative Engine Optimization (GEO) and Answer Engine Optimization (AEO). The primary goal of this team is to structure corporate knowledge, refine data indexing frameworks, and design semantic pipelines so that company products, disclosures, and metrics rank higher and surface accurately within conversational large language model platforms like ChatGPT, Claude, and Gemini.

Responsibilities

• Develop, evaluate, and maintain production-grade Generative Engine Optimization workflows to cleanly index multi-format institutional datasets.
• Implement robust semantic search retrieval architectures using advanced embedding models, document chunking rules, and context routing workflows.
• Design, optimize, and connect conversational retrieval-augmented generation pipelines with secure enterprise vector storage frameworks to minimize processing hallucinations.
• Build stateful multi-agent orchestrations, custom tool-calling frameworks, and self-correcting prompt loops to parse unstructured financial data queries.
• Execute validation benchmarking routines, tracking prompt alignment, context relevance scores, and accuracy metrics across generative platforms.
• Partner actively with backend engineers and database infrastructure specialists to monitor high-volume feature ingestion streams.

Requirements

• Total Experience: Non-negotiable 1 to 4 years of full-time, hands-on industry experience working as an NLP Data Scientist, AI Engineer, or Machine Learning Developer.
• Core Technical Stack: Advanced proficiency in Python programming, automated data scripting, transformer architectures, and structural text classification algorithms.
• Search and RAG Depth: Practical, hands-on experience building retrieval-augmented generation applications, managing vector databases, or structuring semantic search engines.
• Agentic Automation: Foundational experience with agentic frameworks, multi-agent workflow design, complex custom function-calling routines, and prompt engineering utilities.
• Infrastructure Exposure: Familiarity with deploying containerized applications, RESTful microservices development, and managing continuous integration code flows.
• Academic Pedigree: Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Data Science, or an equivalent technical stream from a highly recognized engineering institute.

Skills

• Python
• NLP
• RAG
• Vector Databases
• Prompt Engineering

Benefits

• Flexible schedule
• Provident Fund