RAG ML Engineer II: Retrieval & LLM Orchestration

Jobtailor; Massachusetts; On-site; USD 140,000 - 170,000; Full time

Job summary

Jobtailor is seeking an experienced ML/NLP Engineer to design and implement end-to-end RAG pipelines, combining chunking, embedding models, and vector databases. You will build scalable retrieval systems for large proprietary datasets and orchestrate LLM-based solutions for high-quality, context-aware responses.

You will collaborate with Product, Design, and ML Ops to automate the ML lifecycle from development to deployment in a fast-paced environment.

Qualifications

• Bachelor's degree or higher in Computer Science, Engineering, or a related field.
• 3+ years of hands-on industry experience with ML, NLP, information retrieval, and large-scale text processing.
• Experience designing, shipping, and maintaining production systems.
• Strong Python programming skills.
• Experience with PyTorch, Transformers, and HuggingFace.
• Experience with LangChain and LlamaIndex.
• Knowledge of vector databases and similarity search techniques.

Responsibilities

• Design and implement end-to-end RAG pipelines integrating chunking, embedding models, vector databases, and data retrieval agents.
• Build and optimize retrieval systems over large-scale proprietary datasets using advanced embedding techniques.
• Develop LLM-based solutions orchestrating retrieval, generation, and ranking for context-aware responses.
• Investigate challenges in vector search, chunking/indexing strategies, and unstructured data retrieval evaluation.
• Collaborate with Product and Design teams to build ML-based solutions enhancing user experiences and business objectives.
• Work with ML Operations to automate management of the full ML systems lifecycle from design to implementation.

Skills

RAG pipelines

End-to-end design

Python programming

LLM orchestration

Information retrieval

NLP

Vector databases

Embedding models

Code optimization

Education

Bachelor's degree or higher in CS/Engineering

Tools

PyTorch

Transformers

HuggingFace

LangChain

LlamaIndex

PostgreSQL/PGVector

OpenSearch

Pinecone

Job description

Jobtailor is seeking an experienced ML/NLP Engineer to design and implement end-to-end RAG pipelines, combining chunking, embedding models, and vector databases. You will build scalable retrieval systems for large proprietary datasets and orchestrate LLM-based solutions for high-quality, context-aware responses.

You will collaborate with Product, Design, and ML Ops to automate the ML lifecycle from development to deployment in a fast-paced environment.