4 of 4 Permanent LlamaIndex Jobs in Glasgow

record with the AI Development Life Cycle (AI DLC). Modern AI stack depth: Python/TypeScript, PyTorch, an orchestration framework (LangGraph, LangChain/LlamaIndex, CrewAI, or AutoGen), and vector databases (Pinecone, Qdrant, Weaviate, or Milvus) Model‐serving infrastructure: For example Triton/vLLM as well as LLM gateway products ...

emerging LLM architectures.GenAI Frameworks & Platforms: Proficient with Data & AI platforms (Azure AI, Vertex AI, Databricks, Hugging Face), advanced GenAI frameworks (LangChain, HF Transformers, LlamaIndex) & Agentic architectures (LangGraph, SmolAgents, PydanticAI) Prompt Engineering: Deep prompt engineering & optimization skills for GenAI.Vector DBs & RAG: Designed solutions using vector DBs & Retrieval Augmented GenAI ...

experience in AI/ML with experience developing and deploying solutions using LLMs, RAG architectures, and modern AI frameworks and protocols (Strands, FastMCP, LangChain, LlamaIndex, Hugging Face, A2A, MCP).Ability to translate multi-layered business problems into technical solutions with experience working directly with business stakeholders to understand requirements ...

experience building applications on AWS or other public cloud platformsExperience with Generative AI systems, including: RAG (Retrieval-Augmented Generation) architectureAI orchestration frameworks (LangChain, LlamaIndex, etc.)LLM evaluation frameworks and responsible AI practices (guardrails, content filtering)Preferred Qualifications, Capabilities, and SkillsDeep expertise in Java, object-oriented design, and system designExperience with ...