[Remote] ARF L3 GDC AI Engineer

Note: The job is a remote job and is open to candidates in USA. NR Consulting is looking for an experienced AI Engineer to join their team. The role involves deploying and maintaining AI models, optimizing conversational search functions, and integrating cross-functional systems while collaborating with other engineers.

Responsibilities

• AI Model & Pipeline Implementation: Act as the primary developer for deploying and maintaining AI models and engineering their associated ingestion pipelines
• Vertex AI Search Deployment: Implement a dual-search experience that allows users to utilize both a Vertex AI-powered semantic discovery engine and a traditional faceted keyword search
• Conversational Search Optimization: Develop single-session conversational search functions featuring generative summaries, ensuring strict configuration to index only proprietary content with precise source citations to eliminate open-internet hallucinations
• Intelligent Asset Tagging: Leverage Gemini multimodal models during the ingestion workflow to parse raw, unstructured data (such as PDFs and presentations) and automatically extract/suggest library-science-level metadata tags
• RAG Chatbot Development: Construct and deploy isolated Website Assistant Chatbots using Vertex AI Search and Conversation Agent/Agent Builder to handle Retrieval-Augmented Generation (RAG) based on crawled website and Member Center content
• AI Guardrails & Performance Control: Implement backend controls for tone, persona alignment, temporal weighting (boosting/burying content), token consumption caps, and rate-limiting parameters to manage platform costs and security
• Cross-Functional Integration: Collaborate with cloud and data engineers to stream full inference logs to Google Cloud Storage (GCS) and BigQuery, and ensure proper interface coordination with custom React middleware, Salesforce RBAC permissions, and WordPress sync mechanisms
• Collaboration Framework: Participates in daily scrum ceremonies, technical design review sessions, and rigorous User Acceptance Testing (UAT) quality logging

Skills

• 8+ Years of experience
• Act as the primary developer for deploying and maintaining AI models and engineering their associated ingestion pipelines
• Implement a dual-search experience that allows users to utilize both a Vertex AI-powered semantic discovery engine and a traditional faceted keyword search
• Develop single-session conversational search functions featuring generative summaries, ensuring strict configuration to index only proprietary content with precise source citations to eliminate open-internet hallucinations
• Leverage Gemini multimodal models during the ingestion workflow to parse raw, unstructured data (such as PDFs and presentations) and automatically extract/suggest library-science-level metadata tags
• Construct and deploy isolated Website Assistant Chatbots using Vertex AI Search and Conversation Agent/Agent Builder to handle Retrieval-Augmented Generation (RAG) based on crawled website and Member Center content
• Implement backend controls for tone, persona alignment, temporal weighting (boosting/burying content), token consumption caps, and rate-limiting parameters to manage platform costs and security
• Collaborate with cloud and data engineers to stream full inference logs to Google Cloud Storage (GCS) and BigQuery, and ensure proper interface coordination with custom React middleware, Salesforce RBAC permissions, and WordPress sync mechanisms
• Participates in daily scrum ceremonies, technical design review sessions, and rigorous User Acceptance Testing (UAT) quality logging
• Hands-on experience deploying Vertex AI Search and Vertex AI Conversation / Agent Builder
• Direct experience working with Gemini models for multimodal text parsing, supervised fine tuning, and automated metadata extraction
• Deep understanding of Retrieval-Augmented Generation (RAG) frameworks, semantic discovery, and tuning search metrics like recall precision, chunking quality, and latency
• Familiarity with deploying services across Cloud Run, Firestore, Cloud Workflows, Google Cloud Storage (GCS), and Eventarc
• Experience working with structured data warehouses like BigQuery and streaming inference/activity logs for analytics
• Understanding of how AI APIs interact with external systems, specifically mapping relational metadata to Salesforce canonical IDs and syncing assets with WordPress

Company Overview

Company H1B Sponsorship