remote
Machine Learning Engineer - Agentic Retrieval - Zoom Communications
ML Engineer
Machine Learning Engineer focused on building retrieval and reasoning systems for an AI companion, leveraging Python, PyTorch, LLMs, and distributed cloud infrastructure to deliver trustworthy, enterprise‑scale answers.
About the role
Key Responsibilities
- Design and implement core retrieval and reasoning pipelines that enable AI agents to search, synthesize, and act on enterprise knowledge.
- Develop and fine‑tune large language model components, integrating them with retrieval‑augmented generation techniques.
- Build scalable, multi‑tenant, permission‑aware services using distributed systems principles and cloud platforms (e.g., AWS).
- Collaborate with product, security, and infrastructure teams to ensure high availability, low latency, and data privacy.
- Evaluate model performance, conduct A/B testing, and iterate on metrics for relevance, factuality, and trustworthiness.
Requirements
- Strong programming skills in Python and experience with deep‑learning frameworks such as PyTorch or TensorFlow.
- Hands‑on experience building retrieval‑augmented generation or similar AI‑driven search systems.
- Solid understanding of distributed systems, micro‑services architecture, and cloud services (AWS preferred).
- Proven ability to work with large language models, fine‑tuning, prompt engineering, and evaluation.
- Excellent problem‑solving skills and a track record of delivering production‑grade ML solutions at scale.