Role OverviewWe are seeking a hands-on AI Engineer with deep expertise in Large Language Model integration and production AI systems. This role will lead the design and implementation of LLM-powered capabilities within our platform, working closely with backend, mobile, and product teams.This individual will own the end-to-end AI architecture, from model selection and prompt strategy to retrieval systems, evaluation frameworks, cost optimization, and production deployment.This is not a research role. It is a systems architecture and applied AI engineering role focused on building scalable, secure, real-world AI applications.Key ResponsibilitiesLLM Architecture & IntegrationDesign and implement LLM-powered application workflowsArchitect prompt orchestration, tool calling, and multi-step reasoning pipelinesDefine model selection strategy (OpenAI, Anthropic, open-source models, etc.)Implement streaming responses for mobile and web clientsOptimize token usage and latency for production environmentsBuild fallback and resilience strategies across model providersRAG & Knowledge SystemsArchitect retrieval-augmented generation pipelinesDesign vector database schema and embedding workflowsImplement chunking, metadata tagging, and indexing strategiesOptimize semantic search relevanceIntegrate structured and unstructured data sourcesAI Infrastructure & Backend IntegrationCollaborate with backend architects to integrate AI services into APIsDesign asynchronous processing pipelines for AI workflowsImplement caching strategies for inference resultsArchitect evaluation and monitoring frameworks for LLM output qualityBuild guardrails, moderation layers, and output validationModel Evaluation & PerformanceDefine evaluation metrics for response qualityImplement automated testing for LLM outputsAnalyze hallucination patterns and mitigation techniquesMonitor drift, cost, and performance metricsContinuously improve prompt and architecture strategiesSecurity & GovernanceImplement data privacy safeguardsEnsure compliance with enterprise security requirementsDesign safe handling of user-generated contentImplement access control and audit loggingTechnical LeadershipGuide LLM architecture decisions across the platformMentor engineers working on AI-related componentsEvaluate emerging AI tools and frameworksDefine long-term AI roadmap aligned with product strategyRequired Qualifications5–8+ years in software engineering with at least 2+ years focused on LLM systemsProduction experience integrating LLM APIsStrong experience with:Python (FastAPI preferred)Vector databases (pgvector, Pinecone, Weaviate, etc.)Embeddings and semantic searchPrompt engineering and tool invocation workflowsExperience building RAG systems in productionExperience optimizing latency and inference costsStrong understanding of tokenization, context windows, and model limitationsExperience deploying AI services in cloud environments (AWS, GCP, Azure)Preferred QualificationsExperience with multi-agent orchestration frameworksExperience with LangChain, LangGraph, or similar frameworksExperience with evaluation tooling and benchmarkingFamiliarity with fine-tuning or model adaptation techniquesExperience building AI features for mobile-first applications