Cognitive Architect

Job OverviewThe AI Engineer will be responsible for designing, deploying and maintaining production AI systems for enterprise clients. The role requires expertise in building intelligent systems, architecting vector databases, and fine-tuning pipelines. Strong understanding of software engineering fundamentals and business acumen are essential. The ideal candidate should have a strong background in Python, experience with LLM Orchestration, and knowledge of RAG Systems.This is an exciting opportunity to apply your skills in Artificial Intelligence Engineering and take on new challenges.Key ResponsibilitiesDesign and deploy RAG architectures, multi-agent systems, and LLM-powered applicationsBuild process automation pipelines that replace manual workflows with intelligent agentsImplement fine-tuning pipelines when off-the-shelf models don't cut itShip solutions in 4-8 week sprints that meet enterprise security, scalability, and compliance standardsTechnical SkillsExpert-level Python skills with FastAPI, Pydantic, async programming, and clean architectureExperience with at least two LLM Orchestration tools: LangChain, LangGraph, LangSmith, or LlamaIndexKnowledge of RAG Systems, including vector databases (Pinecone, Weaviate, Qdrant, Chroma), embedding strategies, retrieval optimization, and chunking approachesAgent Frameworks: CrewAI, AutoGen, Pydantic, or custom agent architecturesAutomation Platforms: n8n, Make, Relevance AI, or similarAPIs & Integrations: REST, webhooks, OAuthCloud Platforms: AWS, GCP, AzureRequirements3+ years building production software, not just ML experiments2+ years working specifically with LLMs, RAG, or generative AI in productionTrack record of shipping: show us what you've built