Senior AI Data Engineer

Huxley; United States; Hybrid; USD 150,000 - 250,000; Full time

Benefits offered by this job

Medical coverage

Paid leave

Job summary

Huxley is seeking a Senior AI Data Engineer to design and scale AI infrastructure, focusing on Production RAG systems, vector databases, and LLM integrations within a modern cloud data ecosystem.

In this senior IC role you will own end-to-end data pipelines, build scalable embedding workflows, and collaborate with application engineers to deliver AI-powered features with strong observability and governance.

Qualifications

• 5+ years in Data/AI Engineering or ML infrastructure.
• Hands-on with production RAG systems at scale.
• Strong Python development and cloud data skills.

Responsibilities

• Design, build, and maintain end-to-end RAG pipelines (ingestion, chunking, embeddings, vector indexing, retrieval).
• Develop vector search infrastructure for accurate contextual retrieval.
• Build scalable embedding pipelines for structured and unstructured data.
• Implement LLM-powered features: prompts, validation, latency, fallbacks, costs.
• Create observability for AI performance, retrieval quality, token usage, reliability.
• Collaborate with application engineers to embed AI in products.
• Maintain data pipelines supporting AI workloads with governance and security.
• Evaluate new AI tech and set production best practices.
• Contribute to architecture, standards, CI/CD, testing, operational excellence.

Skills

Data Engineering

AI Engineering

ML Infrastructure

Production RAG systems

LLM APIs

Python

Cloud data platforms

CI/CD

Agile

Tools

Pinecone

pgvector

Chroma

Databricks Vector Search

LangChain

Job description

Senior AI Data Engineer

A high-growth organization is seeking a Senior AI Data Engineer to help build and scale the AI infrastructure that powers next-generation intelligent applications. This is a senior individual contributor role focused on developing production-grade AI systems, Retrieval-Augmented Generation (RAG) architectures, vector search platforms, LLM integrations, and large-scale data pipelines within a modern cloud data ecosystem.

What You'll Be Doing

• Design, build, and maintain end-to-end RAG pipelines, including document ingestion, chunking, embedding generation, vector indexing, and retrieval optimization.
• Develop and manage vector search infrastructure, ensuring highly accurate and contextually relevant retrieval for AI-powered applications.
• Build scalable embedding pipelines for both structured and unstructured data sources.
• Implement and optimize LLM-powered features, including prompt engineering, output validation, latency management, fallback strategies, and cost optimization.
• Develop observability frameworks to monitor AI system performance, retrieval quality, token usage, response quality, and application reliability.
• Collaborate closely with application engineers to integrate AI capabilities into user-facing products.
• Build and maintain data pipelines that support AI workloads while adhering to governance, security, and data quality standards.
• Evaluate emerging AI technologies and recommend best practices for production adoption.
• Contribute to architecture decisions, engineering standards, CI/CD processes, testing frameworks, and operational excellence initiatives.

What They're Looking For

• 5+ years of experience in Data Engineering, AI Engineering, or Machine Learning Infrastructure roles.
• Hands-on experience building and supporting production RAG systems at scale.
• Strong expertise integrating LLM APIs (OpenAI, Anthropic, Google, or similar) into production environments.
• Experience with vector databases and retrieval technologies such as Pinecone, pgvector, Chroma, Databricks Vector Search, or similar platforms.
• Advanced Python development skills and experience building production-quality software.
• Experience with modern cloud data platforms, data pipelines, CI/CD workflows, and data governance practices.
• Strong understanding of AI observability, monitoring, evaluation, and performance optimization.
• Experience working in Agile development environments.

Nice to Have

• Experience with Databricks, Delta Lake, Unity Catalog, or modern lakehouse architectures.
• Familiarity with LangChain, LangGraph, LlamaIndex, or similar AI orchestration frameworks.
• Exposure to agentic AI architectures, tool-calling frameworks, and multi-step AI workflows.
• Knowledge of large-scale distributed processing using PySpark or similar technologies.
• Experience building AI solutions in highly regulated, enterprise, or document-intensive environments.

Ideal Candidate

The ideal candidate has deep experience building reliable AI systems in production and understands what it takes to move beyond proof-of-concept solutions. They're comfortable operating at the intersection of data engineering, machine learning infrastructure, and AI application development, with a strong focus on scalability, observability, reliability, and business impact.

Compensation: Target base salary up to approximately $250K+, depending on experience and level.

Location: Hybrid/onsite opportunity with a well-established, technology-focused organization investing heavily in AI innovation.

EOE Statement: Specialist Staffing Group is an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, or veteran status.

In addition to base pay, direct-hire employees may be eligible for client offered benefits such as medical, dental, and vision coverage, and paid leave where required by applicable law. Eligibility may vary based on factors such as location and hire date and is subject to change.

To find out more about Huxley, please visit www.huxley.com