ML Engineer II — RAG Pipelines & LLM Orchestration

Kensho; Cambridge (MA); On-site; USD 140,000 - 180,000; Full time

Benefits offered by this job

Medical insurance

Dental insurance

Vision insurance

Unlimited PTO

Parental leave 26 weeks

401(k) with company match

Tuition assistance

Job summary

Kensho seeks a mid-level Machine Learning Engineer to design, implement, and scale production-grade RAG pipelines and LLM orchestration across enterprise search and knowledge discovery tasks. You will work with retrieval models, vector databases, and unstructured data sources to deliver context-aware responses.

Join a team focused on building scalable ML systems, collaborating with Product, Design, and ML Ops to automate lifecycle management and deliver robust, end-to-end solutions in a

Qualifications

• 3+ years hands-on industry experience with ML, NLP, information retrieval, and large-scale text processing.
• Experience shipping and maintaining production ML systems.
• Strong programming and collaboration skills.

Responsibilities

• Design end-to-end RAG pipelines with proprietary chunking, embeddings, and data retrieval agents.
• Build and optimize retrieval systems over large datasets.
• Develop LLM-based solutions for orchestrating retrieval, generation, and ranking.
• Investigate vector search, chunking/indexing strategies, and evaluation.
• Collaborate with Product/Design to enhance user experiences.
• Work with ML Ops to automate ML lifecycle from design to deployment.

Skills

ML/NLP experience

Python

LLM orchestration

Vector databases

Education

Bachelor's degree in CS/Engineering or related field

Tools

LangChain

LLamaIndex

PyTorch

Transformers

HuggingFace

OpenSearch

PostgreSQL/PGVector

Docker

Kubernetes

Airflow

Job description

Kensho seeks a mid-level Machine Learning Engineer to design, implement, and scale production-grade RAG pipelines and LLM orchestration across enterprise search and knowledge discovery tasks. You will work with retrieval models, vector databases, and unstructured data sources to deliver context-aware responses.

Join a team focused on building scalable ML systems, collaborating with Product, Design, and ML Ops to automate lifecycle management and deliver robust, end-to-end solutions in a