Senior Data Scientist II – Generative AI / RAG / Agentic AI

Remitly • Raleigh, MA

1d • $104,900 - $209,700 • Hybrid

About The Position

You will join a multidisciplinary team of data scientists, engineers, and product partners focused on building intelligent, reliable, and responsible AI solutions for legal and business professionals. We work collaboratively, value thoughtful experimentation, and prioritize high-quality, production-ready outcomes. As a Senior Data Scientist II, you will design and improve Generative AI, Retrieval-Augmented Generation (RAG), and agentic RAG systems that power drafting, search, and reasoning use cases. You will focus on retrieval quality, evaluation, and production-grade machine learning components, working closely with cross-functional partners to deliver measurable improvements in relevance, accuracy, and user trust.

Requirements

• Proven experience building and improving Generative AI and LLM-based solutions in production or near-production settings
• Strong experience with RAG frameworks, retrieval-based AI architectures, and agentic workflows
• Advanced Python skills, including modular design, testing, debugging, and clean coding practices
• Strong understanding of information retrieval, text search methods, and retrieval architectures
• Hands-on experience with OpenSearch, Solr, or similar search platforms
• Experience with embeddings, semantic retrieval, reranking, and relevance optimization
• Proven ability to work effectively in a monorepo environment with disciplined version control and code review practices
• Experience collaborating in cross-functional teams and contributing to CI/CD and deployment workflows

Responsibilities

• Design, build, and optimize Generative AI, RAG, and agentic RAG systems for drafting, search, and reasoning use cases
• Improve LLM-generated outputs through prompt design, retrieval optimization, evaluation, and experimentation
• Develop and maintain scalable data science and machine learning components for production environments
• Build and enhance retrieval pipelines, including query processing, document retrieval, ranking, reranking, and grounding strategies
• Apply text search and relevance tuning techniques using platforms such as OpenSearch and Solr
• Use embeddings, hybrid retrieval, semantic search, and reranking methods to improve answer quality and system performance
• Write high-quality, maintainable, production-ready Python code following strong software engineering practices
• Collaborate closely with partners across data science, engineering, product, and domain teams

Benefits

• annual incentive bonus

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed