Senior AI/ML Engineer - R01571454

Design, build, and deploy end-to-end AI agent workflows including prompt engineering, tool orchestration, and quality validation layers.

Develop and optimize Retrieval-Augmented Generation (RAG) pipelines focusing on chunking, embedding models, retrieval ranking, and context window management.

Maintain production AI/ML solutions with monitoring, edge case handling, and implement feedback loops for continuous performance improvements.

2-4 years work experience with at least 2 years specifically in building LLM-based apps, RAG systems, or AI agent workflows.

Advanced proficiency in Python and experience with LLM frameworks such as LangChain or LlamaIndex.

Strong expertise in prompt engineering, RAG architectures (embedding models, vector stores, retrieval strategies), and building multi-step agent workflows with tool use and error handling.

Bachelor's degree in Computer Science, Data Science, IT, or related field.

Experienced in production deployment and monitoring of AI/ML solutions, including data pipeline tools like KubeFlow or BentoML.

Demonstrates ability to integrate multi-agent orchestration frameworks and implement feedback mechanisms such as RLHF or expert review data loops.

Familiar with advanced LLM topics including fine-tuning, cost optimization, multi-modal AI systems, and evaluation frameworks for generative AI.