Consultant- Python AI Developer

Thryve Digital · Remote

Source and collection record

Last observed by our collector: 9 October 2026 at 12:26 am IST. This is not a manual review or a confirmation from the employer.

Job type and experience labels are automated discovery categories. The employer determines eligibility. Original experience wording was not retained separately; check the current employer page.

How sourcing and classification work · Report a discrepancy

Your application evidence checklist

Mark the statements you can support after reading the employer source. This checklist stays on this page; it does not score your eligibility or submit an application.

Attendance and availability: I checked the employer page for work location, office attendance, start date and duration.Current requisition: I checked the current employer requisition and its application requirements.

0 of 2 checks marked. Keep unresolved requirements as questions for the employer.

Collected role description

The internal project staffing plan identifies an AI Engineer role whose primary responsibilities include**"Vertex AI Search setup"** and**"prompt tuning for auto-tagging"** as part of the AI-enabled Knowledge Management platform implementation. Job Description: AI Engineer (Vertex AI Search & Prompt Engineering)Position Title AI Engineer (Generative AI & Search Solutions) Experience Required 5-8 Years of Relevant Experience (Including 2-4 years working with AI/ML, LLMs, Search, or Generative AI platforms) Employment Type Full-Time Role Summary We are seeking a skilled AI Engineer to design, implement, and optimize AI-driven search and knowledge discovery solutions. The primary focus of this role will be Vertex AI Search implementation, prompt engineering, and auto-tagging optimization for enterprise knowledge management and content discovery platforms. The ideal candidate will work at the intersection of AI, search, metadata management, and enterprise applications, enabling intelligent search experiences, automated content classification, and Retrieval-Augmented Generation (RAG) capabilities. Key ResponsibilitiesVertex AI Search ImplementationDesign and configure Vertex AI Search for enterprise document repositories.Build search indexing strategies for structured and unstructured content.Configure semantic search and relevance ranking mechanisms.Support content ingestion and indexing pipelines.Optimize search quality, response accuracy, and retrieval performance. The Knowledge Management initiative specifically includes Vertex AI Search setup as a core responsibility of the AI Engineer role. Prompt Engineering & Auto-TaggingDesign, test, and optimize prompts for automated metadata generation.Develop prompt patterns for:Content categorizationTopic extractionKeyword generationKnowledge classificationDocument summarizationMetadata enrichmentImprove precision and consistency of AI-generated tags.Establish prompt evaluation and tuning frameworks.Measure and improve tagging accuracy using feedback loops. The project documentation references Vertex AI-based auto-tagging and metadata generation capabilities as part of the AI-enabled knowledge platform. AI-Powered Content ManagementDevelop AI workflows for automatic content classification.Build metadata extraction pipelines for enterprise documents.Implement automated document tagging and taxonomy alignment.Support knowledge discovery and enterprise search experiences.Improve content findability and search relevance.RAG (Retrieval-Augmented Generation) SolutionsDesign and implement RAG architectures.Configure embedding generation and vector indexing.Develop retrieval pipelines supporting AI assistants and enterprise copilots.Improve context retrieval for Generative AI applications.Optimize document chunking and retrieval strategies. The initiative includes vector indexing and AI-powered knowledge retrieval capabilities. AI Platform IntegrationIntegrate AI capabilities with existing enterprise applications.Collaborate with backend teams to expose AI services through APIs.Work closely with product teams to embed AI features into business workflows.Support AI-powered search, recommendations, and content discovery experiences.Model Evaluation & OptimizationEvaluate prompt effectiveness and model outputs.Establish AI quality metrics and performance benchmarks.Identify hallucination risks and implement mitigation mechanisms.Develop validation frameworks for automated content processing.Monitor AI service utilization and performance.Data & Content EngineeringSupport content ingestion and preprocessing pipelines.Prepare data for indexing and AI processing.Create content transformation workflows.Ensure metadata quality and governance standards.Support migration and onboarding of legacy knowledge repositories.Security & Responsible AIImplement enterprise AI governance standards.Ensure secure handling of proprietary and sensitive content.Follow Responsible AI practices for transparency and fairness.Support compliance and auditability requirements.Required QualificationsExperience5-8 years of software engineering, AI engineering, search engineering, or machine learning experience.Hands-on experience implementing Generative AI solutions.Experience with AI search platforms and enterprise content discovery.Experience with LLM prompt engineering and optimization.Experience designing AI-enabled document processing solutions.Technical SkillsAI & Machine LearningGenerative AILarge Language Models (LLMs)Prompt EngineeringPrompt OptimizationAI Evaluation FrameworksMetadata GenerationText ClassificationSemantic SearchGoogle Cloud & Vertex AIVertex AI SearchVertex AI StudioVertex AI EmbeddingsVertex AI APIsGoogle Cloud Storage (GCS)Cloud RunCloud FunctionsIAM & Security Controls The project's technology stack includes Vertex AI Search, cloud-native deployment, and AI-driven metadata extraction. Search & Retrieval TechnologiesEnterprise SearchSemantic SearchVector DatabasesEmbeddingsRAG ArchitecturesRelevance RankingSearch IndexingProgramming & DevelopmentPythonJavaREST APIsJSONSpring Boot IntegrationGitCI/CD PipelinesData TechnologiesPostgreSQLMetadata ManagementContent RepositoriesDocument ProcessingTaxonomy ManagementPreferred QualificationsExperience implementing Knowledge Management Systems (KMS).Experience with enterprise search platforms.Experience with vector search technologies.Familiarity with agentic AI solutions and AI assistants.Experience in healthcare, insurance, or regulated industries.Google Cloud Professional certifications.Experience with Retrieval-Augmented Generation (RAG) frameworks.Soft SkillsStrong analytical and problem-solving capabilities.Excellent communication and stakeholder engagement skills.Ability to explain AI concepts to technical and business audiences.Strong experimentation mindset.Passion for innovation and emerging AI technologies.Key DeliverablesVertex AI Search ConfigurationSearch Indexing StrategyPrompt Libraries for Auto-TaggingMetadata Generation FrameworkAI Quality & Evaluation ReportsRAG Architecture ComponentsContent Classification ModelsAI Governance DocumentationSuccess Measures The successful candidate will: Deliver highly relevant and accurate enterprise search experiences.Improve metadata quality through automated AI tagging.Increase content discoverability across the organization.Reduce manual content classification effort.Enable AI-powered knowledge retrieval and recommendation capabilities.Establish scalable prompt engineering and governance practices. Primary Technology Stack: Vertex AI Search • Generative AI • Prompt Engineering • Auto-Tagging • Enterprise Search • RAG • Vector Search • Python • GCP • Knowledge Management Systems. Recommended Experience Adjustment for Your KML Program

Collected experience requirement

6 - 9 Years