Senior AI Data Engineer — Scale RAG & Vector AI Systems

Huxley; Boston (MA); Hybrid; USD 225,000 - 275,000; Full time

Job summary

Huxley is seeking a Senior AI Data Engineer to build and scale AI infrastructure powering next-generation intelligent applications. You will own production-grade AI systems, RAG architectures, and large-scale data pipelines in a modern cloud data ecosystem.

The role emphasizes scalable embedding pipelines, vector search, and LLM integrations within a collaborative, fast-growing team. The ideal candidate has 5+ years in data/AI engineering, strong Python skills, and experience with vector

Qualifications

• 5+ years in Data Engineering, AI Engineering, or ML infrastructure.
• Hands-on experience building production RAG systems at scale.
• Strong expertise integrating LLM APIs into production environments.
• Experience with vector databases and retrieval tech (Pinecone, pgvector, Chroma, Databricks Vector Search).
• Advanced Python development for production software.
• Experience with cloud data platforms, CI/CD, and data governance.
• Strong AI observability, monitoring, evaluation, and performance optimization.
• Experience working in Agile environments.

Responsibilities

• Design, build, and maintain end-to-end RAG pipelines (ingestion, chunking, embedding, vector indexing, retrieval).
• Develop and manage vector search infrastructure for accurate retrieval.
• Build scalable embedding pipelines for structured/unstructured data.
• Implement and optimize LLM-powered features including prompts and latency management.
• Develop observability frameworks to monitor AI system performance and reliability.
• Collaborate with application engineers to integrate AI capabilities into products.
• Maintain data pipelines supporting AI workloads with governance and security.

Skills

Data engineering

AI engineering

Machine learning infra

Python

LLM APIs

Agile

Cloud data platforms

Tools

Pinecone

pgvector

Chroma

Databricks Vector Search

LangChain

LangGraph

LlamaIndex

Job description

Huxley is seeking a Senior AI Data Engineer to build and scale AI infrastructure powering next-generation intelligent applications. You will own production-grade AI systems, RAG architectures, and large-scale data pipelines in a modern cloud data ecosystem.

The role emphasizes scalable embedding pipelines, vector search, and LLM integrations within a collaborative, fast-growing team. The ideal candidate has 5+ years in data/AI engineering, strong Python skills, and experience with vector