Senior Ai Engineer

• Build and deploy LLM-powered applications using commercial and open-source models
• Design and implement Retrieval Augmented Generation (RAG) pipelines
• Create AI agents that reason over structured (graph) and unstructured data
• Define and implement tool-use patterns for agents (function calling, API tools, memory tools)
• Apply strong prompt engineering techniques for reliability, safety, and performance
• Design and manage knowledge graphs using Neo4j
• Model complex relationships and optimize graph queries (Cypher)
• Implement semantic search using vector databases
• Apply NLP concepts such as embeddings, entity extraction, classification, summarization, and similarity search
• Set up and operate Model Context Protocol (MCP) servers
• Register datasets, APIs, and tools for secure LLM access
• Enable scalable, observable, and governed LLM interactions
• Build AI microservices using Python (FastAPI / Flask)
• Integrate and consume internal and external APIs within AI workflows
• Develop pipelines for ingestion, embedding generation, indexing, and retrieval
• Evaluate LLM and NLP models using qualitative and quantitative techniques
• Measure and monitor performance (accuracy, latency, cost, hallucinations)
• Continuously iterate on prompts, retrieval strategies, and model configurations

6+ years of AI Engineering experience, or equivalent demonstrated through one or a combination of the following: work experience, training, military experience, education

• Experience with LangChain, LlamaIndex, Semantic Kernel, or similar frameworks
• Cloud experience (Azure preferred
• AWS/GCP welcome)
• Experience with Docker and Kubernetes
• Knowledge of knowledge graphs, ontologies, or semantic systems
• Exposure to AI governance, security, or responsible AI practices