Senior AI Engineer - LLM & RAG Systems

An SF based startup is looking to hire a Senior AI Engineer.

The role is fully remote.

Here's What The Day-to-day Responsibilities Will Look Like -

• Design and implement conversational AI agents using LLMs
• Build RAG pipelines to process e-commerce data
• Optimize prompt engineering for accuracy and cost efficiency
• Create data ingestion pipelines for various formats (CSV, Excel, APIs)
• Implement opportunity detection algorithms
• Ensure system scalability for processing 10,000+ SKUs
• Collaborate on architecture decisions

Here are some key traits that we are looking for -

LLM Engineering Experience

Previous experience building AI agents

Prompt engineering and optimization

RAG (Retrieval Augmented Generation) implementation

Experience working with LLMs like OpenAI API, Anthropic Claude, or similar

Understanding of token optimization and context window management

Vector Database & Embeddings

Hands-on experience with Pinecone, Weaviate, Qdrant, or pgvector

Understanding of embedding models and semantic search

Experience with chunking strategies for documents

Data Pipeline Experience

ETL / data ingestion from CSVs, APIs, databases

Data normalization and schema mapping

Experience with real-time data processing

Skills Required

semantic search