Machine Learning Engineer

About the role

You will work directly on the systems that sit at the core of our AI products. That means building and maintaining ML pipelines, designing retrieval-augmented generation architectures, and helping integrate research results into production systems. We move fast and expect engineers to own their work end-to-end.

What you will do

• Build and maintain ML pipelines for production use across healthcare and legal domains
• Design and implement retrieval-augmented generation (RAG) architectures
• Develop and evaluate multi-agent systems for complex reasoning tasks
• Collaborate closely with research and product teams to bring models into production
• Profile and optimize model performance and inference latency

What we are looking for

• Strong Python skills and familiarity with ML frameworks (PyTorch, HuggingFace, etc.)
• Hands-on experience building and deploying LLM-based applications
• Solid understanding of retrieval systems, vector databases, and embeddings
• Experience with cloud infrastructure (AWS, GCP, or Azure) for ML workloads
• Ability to read and implement ideas from ML research papers

Nice to have

• Experience with multi-agent frameworks (LangGraph, AutoGen, etc.)
• Prior work in healthcare or legal technology
• Familiarity with operations research or optimization methods