Applied Scientist, Multi-Agent AI for Compliance

Blee, Inc.; San Francisco (CA); Hybrid; USD 170,000 - 230,000; Full time

Benefits offered by this job

Equity package

Bi-annual off-sites

Medical, dental, and vision insurance

OneMedical access (US)

Life insurance

401k + matching

Flexible time off (15 days)

Learning opportunities

Job summary

Blee, Inc. is seeking an Applied Scientist to architect multi-agent systems that blend foundational and custom models to surface, track, and explain compliance flags.

You will build and optimize AI/ML pipelines, fine-tune models, and design evaluation frameworks to deliver accurate, explainable results. You will collaborate with product and engineering teams to integrate AI features via APIs and data pipelines, while ensuring transparency, reliability, and continuous improvement across

Qualifications

• 5+ years of applied ML/AI engineering experience.
• Strong knowledge of agent-based architectures and orchestration frameworks.
• Proficient in Python and modern software practices (APIs, microservices, distributed systems).
• Experience with ML frameworks such as PyTorch, TensorFlow or Hugging Face.
• LLM experience: fine-tuning, prompt engineering, RAG, evaluation.
• Experience building data preprocessing, feature engineering and training pipelines.
• Production ML: model serving, monitoring and A/B testing, data pipelines.
• Strong cross-functional collaboration and communication.

Responsibilities

• Architect multi-agent systems – Design and implement frameworks that integrate foundational LLMs and custom-trained models to power intelligent compliance workflows
• Build and optimize AI/ML pipelines – Model fine-tuning, prompt engineering, and evaluation frameworks
• Ensure explainability and traceability – Build mechanisms for transparent flagging, ensuring every compliance flag is traceable to prior rules, examples, or data assets
• Automate compliance rule translation – Build systems that transform compliance rules into agent-ready logic paths
• Design, train, and fine-tune models – Improve compliance accuracy and adaptability using user feedback and outcomes data to drive iterative training and personalization
• Design model evaluation and monitoring infrastructure – Ensure reliability and auditability across customer deployments
• Collaborate cross-functionally – Work with Product Engineers to integrate AI features via APIs, data pipelines, and frontend; partner with model training engineers to incorporate feedback loops into system design; collaborate with compliance users to translate complex rules into agent workflows
• Stay current on AI/ML advances – Prototype and apply new techniques to our platform

Skills

Applied ML/AI engineering

Python

ML frameworks

LLM fine-tuning

Data preprocessing

Production ML

APIs & microservices

Model monitoring

Cross-functional collaboration

Communication

Tools

PyTorch

TensorFlow

Hugging Face

Job description

Blee, Inc. is seeking an Applied Scientist to architect multi-agent systems that blend foundational and custom models to surface, track, and explain compliance flags.

You will build and optimize AI/ML pipelines, fine-tune models, and design evaluation frameworks to deliver accurate, explainable results. You will collaborate with product and engineering teams to integrate AI features via APIs and data pipelines, while ensuring transparency, reliability, and continuous improvement across