Machine Learning Engineer II
Core
Design and implement end-to-end RAG pipelines, build and optimize retrieval systems over large-scale proprietary datasets, and develop LLM-based solutions for orchestration.
Role type
Mid-level Machine Learning Engineer (RAG & Retrieval Systems)
Builds
Production-grade RAG systems, retrieval-driven search pipelines, and agentic search solutions for enterprise platforms.
Domain
Financial services, Generative AI, Information Retrieval, NLP
Deliverable
production ML models
Required skills
Python, PyTorch, Transformers, HuggingFace, LLM orchestration (LangChain, LLamaIndex), vector databases (PostgreSQL/PGVector, OpenSearch, Pinecone), similarity search, vector indexing, data processing pipelines
Preferred skills
Agentic Search, Prompt Engineering, GraphRAG, AI agent evaluation, Airflow, Docker, Kubernetes, Jenkins, AWS, Github Action
Responsibilities
Design and implement end-to-end RAG pipelines integrating chunking algorithms and vector databases; Build and optimize retrieval systems using advanced embedding techniques; Develop LLM-based solutions for retrieval, generation, and ranking; Investigate challenges in vector search, chunking, indexing, and unstructured data retrieval evaluation; Collaborate with Product and Design teams to build ML-based solutions; Work with ML Operations to manage the ML systems lifecycle.
Seniority
Mid-level, hands-on IC