About the CompanyGloPros is the all-in-one recruitment platform empowered by AI, delivering intelligent, scalable solutions for companies and talent. We build sophisticated, high-performance web experiences infused with AI to transform how organizations hire and how professionals advance their careers.The GloPros TeamJoin a dynamic, ambitious, and innovative team that values creativity, collaboration, and continuous learning. We foster a culture where your voice matters, and you'll work alongside professionals who are passionate about shaping the future of AI-powered hiring. Regular social events and daily team lunches make our office a welcoming place to connect, share ideas, and have fun.About the RoleWere seeking an experienced Full Stack AI Engineer to architect and build our Search Engine v2 powered by Weaviate and our intelligent HR integration platform. Youll work directly with our CTO and Head of Product to bring breakthrough features to life, starting with our AI Recruitment Agent that reimagines the entire hiring workflow. This is a high-impact role where youll own significant technical initiatives from conception to production, directly shaping how thousands of users experience our platform daily.ResponsibilitiesSearch Engine v2 (Weaviate-Powered)Architect Glopros's core search infrastructure using Weaviate as our vector database foundationDesign and implement Hybrid Search leveraging Weaviate's native capabilities for superior semantic understandingBuild multi-tenant search experiences tailored to three user personas: clients searching for candidates, candidates discovering opportunities, and recruiters managing pipelinesDevelop intelligent re-ranking algorithms that consider user context, historical interactions, and real-time signalsCreate real-time indexing pipelines that process candidate profiles, job descriptions, interview feedback, and interaction dataOptimize Weaviate schemas, collections, and query patterns for sub-second latency at scaleImplement cross-referencing and graph-based retrieval to surface hidden candidate-opportunity matchesAI Recruitment Agent and other AI featuresBuild autonomous agent workflows using LangChain and LangGraph that handle candidate screening, scheduling, and follow-upsDesign multi-agent systems that collaborate to move candidates through hiring stages intelligentlyCreate conversational interfaces where the agent can interact naturally with candidates, hiring managers, and recruitersDevelop decision-making logic that knows when to escalate to human recruiters vs. handle autonomouslyIntegrate with communication channels (email, SMS, Slack) for seamless agent-human handoffsHR Integration PlatformArchitect bidirectional sync systems with major ATS platforms (Greenhouse, Workday, Lever, Ashby, HiBob, Personio, SAP HCIS)Build automated enrichment pipelines that extract structured insights from interviews, resumes, and performance conversationsDesign fault-tolerant integration frameworks ensuring data consistency across Glopros, client ATS systems, and WeaviateImplement idempotency patterns preventing data duplication during high-volume syncsCreate real-time webhooks that keep all systems synchronized as hiring workflows progressWorkflow Improvements Across User TypesFor Clients (Hiring Managers): Build intuitive candidate discovery tools, automated candidate ranking, and interview scheduling automationFor Candidates: Create personalized job matching, application tracking, and intelligent career guidance featuresFor Internal Recruiters: Develop pipeline management dashboards, AI-assisted candidate screening, and automated administrative task handlingQualifications7+ years building production-grade LLM applications and agentic systemsAI-first coding with Claude, Cursor, and WindsurfHands-on experience with Weaviate or similar vector databases in production environmentsDeep expertise in Python and modern AI frameworks (LangChain, LangGraph, OpenAI API)Proven experience architecting RAG systems and hybrid search implementationsStrong understanding of vector embeddings, semantic search, and retrieval optimizationProduction experience with FastAPI, microservices architecture, and distributed systemsHands-on experience with AWS, Kubernetes, and DockerTrack record of building fault-tolerant, scalable backend features handling real-time dataRequired SkillsCore AI/ML Stack:Vector Database: Weaviate (schema design, hybrid search, GraphQL queries, tenant isolation)LLM Frameworks: OpenAI API, AnthropicRAG & Retrieval: Embedding models, semantic search optimization, re-ranking strategies, RAGAS evaluationLLM Ops: Prompt engineering, agent evaluation, fine-tuningBackend & Infrastructure: Languages: Python (required), Frameworks: FastAPI, Django, Databases: PostgreSQLCloud: AWS (Lambda, ECS, S3), Kubernetes, DockerDevOps: CI/CD (Gitlab Actions), monitoring (Sentry), logging (CloudWatch)Integration & APIs: REST APIs, webhooks, contract-first development (OpenAPI/Anthropic)Experience with ATS platforms (Greenhouse, Workday, Lever, HiBob, Personio) is a major plusReal-time synchronization patterns and idempotency handlingPreferred SkillsPrevious experience in recruitment tech, HR tech, or marketplace platformsUnderstanding of multi-tenant SaaS architecture and data isolation patternsKnowledge of information retrieval theory and learning-to-rank algorithmsExperience building conversational AI agents or chatbotsFamiliarity with data privacy regulations (GDPR, ISO compliance)Contributions to Weaviate or related open-source projects