The RoleThis 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 agents-powered by custom and foundational models-work 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 - 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
Who You Are- Deeply technical and hands-on - you love building production ML systems, not just prototyping
- Customer-outcome oriented - 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 WithYou will work closely with Blee's AI and engineering leadership, collaborating daily with product engineers and implementation managers.
Requirements- 5+ 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, evaluation
- Background in data preprocessing, feature engineering, and training pipelines
- Production ML: model serving, monitoring, A/B testing, data pipelines
- Strong communication skills and ability to work cross-functionally
- Based in the Bay Area or NY & willing to come into the office 3 days a week
How We Work:We have offices in New York and San Francisco and value in-person collaboration, but we're open to remote for the right person. Wherever you're based, expect bi-annual off-sites and the chance to spend time in our other offices when it matters.
What You'll Get:- Competitive salary and equity package
- Bi-annual get-togethers
- Fully paid medical, dental, and vision insurance
- Free access to OneMedical (US Only)
- Company-paid life insurance (US Only)
- Company-sponsored 401k + matching (US Only)
- Flexible time off (with mandatory 15 days off)
- Financial support for work-adjacent learning opportunities
