AI Engineer

Overview

AI Engineer — Onsite 4 days each week in Pittsburg, PA or Memphis, TN
.

• LLM integration (OpenAI, Anthropic Claude, Gemini) - API usage, prompt engineering, context management
• Retrieval-Augmented Generation (RAG) - vector search, chunking strategies, embedding pipelines
• Semantic search - vector stores (Qdrant, Pinecone, Weaviate), similarity scoring, reranking
• Embedding models - OpenAI text-embedding-*, Cohere, open-source (BGE, E5)
• Agent frameworks - Lang Chain, Llama Index, Semantic Kernel, or custom orchestration
• Model Context Protocol (MCP) - tool exposure, resource patterns for LLM agents
• Agentic workflows - multi-step reasoning, tool use, function calling, thinking/reflection loops

• Backend development - Go, Python, or Type Script/Node
• API design - REST and Graph
  
  QL; integrating LLM responses into structured APIs
• Event-driven architecture - async pipelines for ingestion, enrichment, and inference
• Graph databases - Neo4j for knowledge graphs and dependency mapping
• Vector databases - Qdrant, pgvector, or equivalent
• Containerisation - Docker, Kubernetes; deploying inference workloads
• Observability - tracing LLM calls, latency, token usage, quality metrics

• Data ingestion pipelines - structured and unstructured source processing
• Knowledge graph construction - entity extraction, relationship mapping
• Context window management - chunking, summarisation, compression strategies
• Source attribution and citation - grounding responses in verifiable data