Duration: 12+ months
Compensation: OPEN
Location: On-site in either Pittsburgh, PA or Memphis, TN
Seeking an AI Engineer with strong experience building LLM-powered applications, RAG pipelines, semantic search solutions, and agentic AI workflows.
Requirements:- LLM integration:
- OpenAI
- Anthropic Claude
- Gemini
- Prompt Engineering, Context Management, Function Calling
- RAG / Semantic Search / Embedding Pipelines
- Vector DBs:
- Qdrant
- Pinecone
- Weaviate
- pgvector
- LangChain, LlamaIndex, Semantic Kernel, or custom orchestration
- Agentic AI workflows / multi-step reasoning
- Python, Go, or TypeScript/Node.js
- Embedding models, Cohere, BGE, E5
- REST / GraphQL APIs
- Neo4j / Knowledge Graphs
- Docker / Kubernetes
- Async / Event-Driven Architectures
- LLM observability, tracing, token usage, quality metrics
Responsibilities:- Build scalable AI-enabled platforms and APIs
- Develop RAG and semantic search pipelines
- Design agentic AI workflows
- Build ingestion/enrichment pipelines for structured & unstructured data
- Optimize context management and grounding/citation strategies
- Partner with Product and Engineering teams on AI initiatives
26-00459