RAG ML Engineer — Retrieval & LLM Orchestration

S&P Global, Inc.; New York (NY); On-site; USD 140,000 - 180,000; Full time

Benefits offered by this job

Medical, Dental, and Vision insurance

Unlimited Paid Time Off

Parental Leave (26 weeks)

Job summary

Kensho, S&P Global’s AI innovation hub, seeks a mid-level Machine Learning Engineer to scale RAG systems and LLM orchestration across the company. You will design end‑to‑end pipelines, optimize large-scale retrieval, and collaborate with product teams to deliver context‑aware responses.

The role emphasizes hands‑on ML, embedding models, vector databases, and production‑grade systems, with core tech including PyTorch, Transformers, LangChain.

Qualifications

• Bachelor's degree or higher in Computer Science, Engineering, or related field.
• 3+ years of hands-on ML experience including NLP, information retrieval and production systems.
• Strong Python and ML framework skills (PyTorch, Transformers, HuggingFace).
• Experience with LLM orchestration tools (LangChain, LLamaIndex).
• Proven ML pipelines experience across data processing, training, inference, and experimentation.
• Experience with vector databases and similarity search techniques.

Responsibilities

• Design end-to-end RAG pipelines integrating chunking, embedding, vector databases and data retrieval agents.
• Build and optimize retrieval systems over large proprietary datasets with advanced embeddings.
• Develop LLM-based solutions to orchestrate retrieval, generation and ranking for contextual responses.
• Investigate vector search, indexing strategies, evaluation of unstructured data retrieval and GraphRAG.
• Collaborate with Product/Design to build ML-based user experiences aligned with business goals.
• Work with ML Ops to automate ML lifecycle from design to deployment.

Skills

Python

Machine Learning

NLP

Information Retrieval

RAG pipelines

LangChain

PyTorch

Transformers

HuggingFace

Vector databases

Education

Bachelor's degree in CS or related field

Tools

PostgreSQL/PGVector

OpenSearch

Pinecone

Job description

Kensho, S&P Global’s AI innovation hub, seeks a mid-level Machine Learning Engineer to scale RAG systems and LLM orchestration across the company. You will design end‑to‑end pipelines, optimize large-scale retrieval, and collaborate with product teams to deliver context‑aware responses.

The role emphasizes hands‑on ML, embedding models, vector databases, and production‑grade systems, with core tech including PyTorch, Transformers, LangChain.