Machine Learning Engineer, Platform
Core
Building retrieval and knowledge representation systems (RAG pipelines, vector stores, knowledge graphs) for an enterprise-grade Generative AI platform to power agentic workflows.
Role type
Senior IC Machine Learning Engineer (Platform/Retrieval)
Builds
Production retrieval systems, RAG pipelines, knowledge graphs, and context engines for enterprise AI agents.
Domain
Generative AI, Enterprise Software, Knowledge Representation
Deliverable
production ML models
Required skills
Python, RAG pipelines, vector indexing, knowledge graphs, embedding models, evaluation frameworks, backend services, data pipelines
Preferred skills
Ontologies, semantic search, agentic systems, high-growth startup experience, ambiguous problem spaces
Technologies
Vector databases, APIs, LLMs
Responsibilities
Own large areas of platform end to end from design to production deployment; Design and implement RAG pipelines including chunking, embedding, indexing, retrieval, and reranking; Build and maintain integrations between retrieval components and enterprise data sources; Develop context retrieval systems balancing recall, precision, latency, and cost; Build evaluation frameworks and datasets to measure retrieval quality and agent performance; Build reliable backend services and data pipelines supporting ML and LLM components.
Seniority
Senior, hands-on IC
