Qualifications
Key Responsibilities1. AI Core Architecture DesignCraft AI-first system architectures tailored for web and mobile applications. Architect RAG pipelines utilizing vector databases. Define systems for long-term memory, short-term memory, and contextual states. Implement multi-agent AI systems. Design AI orchestration layers.2. Vector Database & Embedding SystemsChoose and implement vector databases including:PineconeWeaviateQdrantMilvusSupabase (pgvector)Refine embedding strategies. Execute hybrid search techniques (semantic + keyword). Design scalable indexing pipelines.3. LLM Integration & OptimizationCollaborate with models like:OpenAI APIsAnthropicMeta (LLaMA)DeepSeekAlibaba (Qwen)Implement structured output pipelines. Establish evaluation and prompt testing frameworks. Optimize the cost-performance ratio.4. AI Agent Systems & OrchestrationConstruct autonomous AI agents. Design tool-calling systems. Integrate with:n8nLangGraph / LangChain style agent flows. Develop memory-aware agents.5. Production AI EngineeringEstablish monitoring systems for detecting hallucinations. Design guardrails and validation layers. Implement evaluation datasets and benchmarking. Ensure the security of AI pipelines. Develop scalable infrastructure (Docker, Kubernetes, GPU optimization). Technical Expertise5+ years of software engineering experience.2+ years of experience in building production AI systems. In-depth knowledge of:Vector embeddings & similarity search. RAG architectures. Tokenization and context window optimization. Fine-tuning & LoRA concepts. Prompt evaluation frameworks. Proficiency in Python (mandatory). Experience with FastAPI / backend services. Expertise in designing scalable APIs.
About the job
We are on the lookout for a seasoned AI Systems Architect to spearhead the design and deployment of AI-native application cores, integrating Large Language Models (LLMs), vector databases, retrieval systems, and agent frameworks as the foundational computational layer for our web and mobile applications.
This pivotal role entails the architecture of scalable AI pipelines, retrieval-augmented generation (RAG) systems, memory architectures, AI agents, and orchestration workflows that harmonize with our development stack (Web, Mobile, n8n automation, and AI services).
The ideal candidate will recognize that AI transcends being merely a feature; it is the very operating system of our product.
About star-sa
star-sa is at the forefront of AI-driven technology solutions, dedicated to innovation and excellence in creating intelligent systems that empower businesses and enhance user experiences. Our commitment to pushing the boundaries of artificial intelligence drives our mission to deliver exceptional products and services.
