Machine Learning Engineer II

What you'll do

• Design and implement end-to-end RAG pipelines using proprietary chunking algorithms, embedding models, and vector databases.
• Build and optimize retrieval systems over large-scale datasets using advanced embedding techniques.
• Develop LLM-based solutions to orchestrate retrieval, generation, and ranking for context-aware responses.
• Solve technical challenges in vector search, indexing strategies, and GraphRAG implementations.
• Create automated solutions with the ML Operations team to manage the full machine learning systems lifecycle.
• Build ML-based features that improve user experience and meet specific business objectives.

What we're looking for

• Bachelor's degree or higher in Computer Science, Engineering, or a related field.
• 3+ years of hands-on industry experience with machine learning, NLP, information retrieval systems, and large-scale text processing.
• Strong programming skills in Python and knowledge of data processing tools and ML frameworks like PyTorch, Transformers, and HuggingFace.
• Experience using LLM orchestration libraries such as LangChain or LlamaIndex.
• Proven experience building ML pipelines for data processing, training, inference, maintenance, evaluation, versioning, and experimentation.
• Experience with vector databases (e.g., PostgreSQL/PGVector, OpenSearch, Pinecone) and understanding of similarity search and indexing algorithms.
• Demonstrated effective coding, documentation, collaboration, and communication habits.
• Strong problem-solving skills and a proactive approach to addressing challenges in a fast-paced environment.