Senior AI Engineer (LLMs & Knowledge Graphs)

Requirements

• 3+ years of strong Python engineering experienceMust
• Working knowledge of knowledge graph modeling (schemas, ontologies, entity resolution)Must
• Hands-on experience with graph databases (Neo4j, Memgraph, AWS Neptune, ArangoDB)Must
• Hands-on experience building RAG pipelines and agentic workflowsMust
• Comfort with prompt engineering and tool/function callingMust
• Experience with fine-tuning and adaptation patterns (LoRA/QLoRA, instruction tuning, embedding model fine-tuning)Must
• Familiarity with LLM evaluation frameworks (Ragas, DeepEval, Langfuse)Must
• Experience with text-to-SQL or semantic parsing capabilities over structured dataMust
• Lexical, vector, and hybrid retrieval with embeddings and rerankingMust
• Solid knowledge of APIs, microservices, and data-centric integrationsMust
• Experience with AWS, Azure, or GCP and CI/CD workflowsMust
• Solid software engineering fundamentals (clean code, testing, debugging, code reviews)Must
• Comfort working in agile pods and collaborative environmentsMust
• Excellent problem-solving skills and attention to detailMust
• Consultancy mindset with ability to find solutions for client needsMust
• Familiarity with Graph Neural Networks (GCN/GAT) and graph embeddings

What you'll do

• Build and implement agentic workflows with orchestration and retrieval pipelines
• Build hybrid search pipelines (lexical + vector) and integrate vector databases (FAISS, Milvus, Pinecone)
• Integrate LLMs (Azure OpenAI, Anthropic) and support domain-specific fine-tuning or adapter models
• Create evaluation suites for reliability, drift detection, and performance optimization
• Design experiments and build evaluation harnesses for model quality, robustness, and bias
• Develop robust API endpoints and ETL pipelines to support model and agent runtimes
• Ability to participate in and lead technical discussions

About the role

Our client, a Fortune 50 leader in enterprise solutions and innovations, is seeking a Senior AI Engineer with Knowledge Graphs and LLMs skills to join their AI incubator to scout, incubate, and validate internal ideas. This role is part of a high-impact strategy leveraging Graph Neural Networks (GNNs) and Generative AI to redefine workflows, semantic search, and intelligence for enterprise solutions in Finance, Operations, Supply Chain, Engineering, or Investments. This is a long-term remote-first contract position with a required overlap of US working hours (2-6 PM CET) . Responsibilities • Build Agentic Workflows: Implement orchestration, retrieval pipelines, and validator agents using graph-aware tools. • Optimize Retrieval: Build hybrid search pipelines (lexical + vector) and integrate vector databases like FAISS, Milvus, or Pinecone. • Model Integration: Integrate LLMs (Azure OpenAI, Anthropic) and support domain-specific fine-tuning or adapter models. • Scalable Engineering: Develop robust API endpoints and ETL pipelines to support model and agent runtimes. • Experiment & Evaluate: Create evaluation suites for reliability, drift detection, and performance optimization. Work Conditions • Type: Full-time & Long-term contract work • Start Date : ASAP • Location : Remote (99%) in Europe; must be able to travel freely within Europe for workshops. • US Time Zone Overlap : Required ( 2 PM - 6 PM CET ) • Contract with European LLC Requirements • Python Expertise: 3+ years of strong Python engineering experience. • Graph Intelligence and Databases: Working knowledge of knowledge graph modeling (schemas, ontologies, entity resolution) and graph databases. Hands-on experience with Neo4j, Memgraph, AWS Neptune, ArangoDB, or similar. Familiarity with graph embeddings and GNNs (GCN/GAT) is a plus. • Evaluation & Experimentation: Comfortable designing experiments, building eval harnesses, and reasoning about model quality, robustness, and bias in production AI systems. • Modern AI Patterns: Hands-on experience building RAG pipelines and agentic workflows. Comfort with prompt engineering and tool/function calling. Experience building text-to-SQL or semantic parsing capabilities over structured data sources. • LLM Observability: Familiarity with LLM evaluation frameworks (e.g., Ragas, DeepEval, Langfuse) and production monitoring of AI systems. • Retrieval & Search: Lexical + vector + hybrid retrieval, embeddings, and reranking. Experience incorporating user and context signals for personalization. • Fine-tuning & Adaptation: Experience with fine-tuning and adaptation patterns (e.g., LoRA/QLoRA, instruction tuning, embedding model fine-tuning). • APIs & Integrations: Solid knowledge of APIs, microservices, and data-centric integrations. • Engineering Discipline: Solid software engineering fundamentals - clean code, testing, debugging, code reviews, and comfort working in agile pods. • Cloud & Deployment: Experience with AWS/Azure/GCP and CI/CD workflows. • Excellent problem-solving skills and keen attention to detail. • Ability to participate in the discussions and lead the technical discussions • Have a consultancy mindset → always try to find a solution for the client Highlights If you are passionate about AI, Graph-centric AI , Python , and building next-generation agentic workflows , this role with our client offers an exciting opportunity to work on cutting-edge R&D projects! Originally posted on Himalayas