ML Engineer II: RAG Pipelines & LLM Orchestration

Kensho Technologies; 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

401(k) with 6% match

Tuition assistance

Conferences/learning opportunities

Dog-friendly office

Job summary

Kensho Technologies in New York, NY, seeks a mid-level Machine Learning Engineer to design and scale RAG pipelines, focusing on retrieval models, LLM orchestration, and system-level thinking. You will work with embedding techniques and proprietary data, contributing to enterprise search, knowledge discovery, and decision-support systems.

The role requires hands-on ML/NLP experience, Python expertise, and production ML tooling.

Qualifications

• Bachelor's degree in Computer Science, Engineering, or related field.
• 3+ years hands-on ML/NLP experience including production systems.
• Strong Python skills and ML frameworks (PyTorch, Transformers, HuggingFace).

Responsibilities

• Design end-to-end RAG pipelines with embedding models and data retrieval agents.
• Build and optimize retrieval systems over large proprietary datasets.
• Develop LLM-based solutions for retrieval, generation, and ranking.
• Solve challenges in vector search, indexing, and unstructured data retrieval.
• Collaborate with Product/Design to meet business objectives.
• Work with ML Ops to manage ML systems lifecycle.

Skills

Python programming

NLP

Information retrieval

LLM orchestration

Vector databases

LangChain/LlamaIndex

Education

Bachelor's degree in CS/Engineering or related field

Tools

LangChain

LLamaIndex

PyTorch

Transformers

HuggingFace

OpenSearch

PostgreSQL/PGVector

LiteLLM

Job description

Kensho Technologies in New York, NY, seeks a mid-level Machine Learning Engineer to design and scale RAG pipelines, focusing on retrieval models, LLM orchestration, and system-level thinking. You will work with embedding techniques and proprietary data, contributing to enterprise search, knowledge discovery, and decision-support systems.

The role requires hands-on ML/NLP experience, Python expertise, and production ML tooling.