AI Engineer

$150K - $210K 30% - 1.00% 3 San Francisco, CA, US Job type Full-time Role Engineering, Machine learning Experience 3+ years

About the role

About Blee

At Blee we are replacing workflows that typically run on spreadsheets, email, etc with AI-first software that brings the whole org together to meet compliance requirements faster, more thoroughly, and with greater transparency. We currently have thousands of active users from dozens of enterprise-grade customers on pledged, or paid, long-term contracts. Our leadership group hails from the likes of Adobe, Chime, PayPal, AWS, Wachtell, Harvard Law, and Columbia Law. We have built the first platform that handles the unique challenges our customers face from front-to-back. We find the ideal people for Blee will not only be natural problem solvers but will also enjoy the thrill of discovering which problems our users need solving in the first place, most of whom have never used a product like Blee before. We have an office in downtown SF, one in NYC coming soon, and most of our team is split between the Bay Area and NYC.

The Role

This is an AI Engineer role specializing in agent system design for someone who wants to architect and implement the next generation of intelligent compliance systems. You will design frameworks where multiple agents1powered by custom and foundational models1work together to surface, track, and explain compliance flags. You will also build and optimize applied AI/ML pipelines, work across model fine-tuning, prompt engineering, evaluation frameworks, and customer-specific AI configurations, and train models based on user feedback to provide more targeted compliance recommendations.

What You'll Do

• Architect multi-agent systems 6 Design and implement frameworks that integrate foundational LLMs and custom-trained models to power intelligent compliance workflows
• Build and optimize AI/ML pipelines 6 Model fine-tuning, prompt engineering, and evaluation frameworks
• Ensure explainability and traceability 6 Build mechanisms for transparent flagging, ensuring every compliance flag is traceable to prior rules, examples, or data assets
• Automate compliance rule translation 6 Build systems that transform compliance rules into agent-ready logic paths
• Design, train, and fine-tune models 6 Improve compliance accuracy and adaptability using user feedback and outcomes data to drive iterative training and personalization
• Design model evaluation and monitoring infrastructure 6 Ensure reliability and auditability across customer deployments
• Collaborate cross-functionally 6 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 6 Prototype and apply new techniques to our platform

Who You Are

• Deeply technical and hands-on 6 you love building production ML systems, not just prototyping
• Customer-outcome oriented 6 you care about how your models perform in the real world, not just on benchmarks
• A fast learner who thrives at the intersection of AI and domain-specific problems, especially compliance and governance
• Strong collaborator who can work across engineering, product, compliance, and customer-facing teams
• Proactive and curious; you stay ahead of the rapidly evolving AI landscape
• Excited to work in a high-trust, high-autonomy environment where your work directly impacts customers

Who You'll Work With

You will work closely with Blee's AI and engineering leadership, collaborating daily with product engineers and implementation managers.

Requirements

• 3 years of applied ML/AI engineering experience
• Strong knowledge of agent-based architectures and orchestration frameworks
• Strong Python; proficiency with modern software engineering practices (APIs, microservices, distributed systems)
• ML frameworks (PyTorch, TensorFlow, Hugging Face)
• LLM experience: fine-tuning, prompt engineering, RAG (Retrieval-Augmented Generation), evaluation
• Background in data preprocessing, feature engineering, and training pipelines
• Production ML: model serving, monitoring, A/B testing,data pipelines
• Strong communication skillsand ability to work cross-functionally
• Based in the Bay Area & willing to come into the office3 days a week
• Authorized to work in the U.S.on a permanent basis without sponsorship

Location

San Francisco Bay Area (office in downtown SF), with an upcoming NYC office; candidate must be based in Bay Area & willing to come into office3 days a week.

Remote Work Allowance

Not explicitly mentioned; requires coming into office3 days a week.

Employment Type

Full-time

Experience Level

Mid-level (3+ years experience)

Salary Range

$150K - $210K base salary plus0.30% -1.00% equity

Skills

• Applied ML/AI engineering (3+ years)
• Agent-based architectures & orchestration frameworks
• Python programming (strong)
• Modern software engineering practices: APIs/microservices/distributed systems
• ML frameworks: PyTorch / TensorFlow / Hugging Face
• Large Language Models (LLM): fine-tuning / prompt engineering / RAG / evaluation
• Data preprocessing & feature engineering
• Training pipelines
• Production ML: model serving / monitoring / A/B testing / data pipelines
• Communication & cross-functional collaboration skills