Senior Applied AI Engineer (Python + LLM Systems)

Descrição da Vaga

Requisitos

• This is an opportunity to have significant technical impact in a real-world fintech environment
• When applying, please include a brief description of one AI-powered feature, service, or system you helped build or support in production
• 5+ years of software engineering experience, including strong backend or systems development experience
• Experience designing and building backend services or distributed systems
• Experience integrating LLM APIs, generative AI services, or AI-enabled capabilities into production systems
• Experience evaluating or improving AI model performance in production environments
• Strong problem-solving and systems design skills
• Ability to collaborate effectively in a cross-functional team
• Experience with FastAPI or similar frameworks
• Experience with model fine-tuning, retrieval-augmented generation (RAG), prompt evaluation, or LLM evaluation methods
• Experience building internal tooling or infrastructure supporting AI applications
• Experience working with vector databases or AI data pipelines
• Experience working in fintech or B2B SaaS environments
• Collaborate in a remote-first environment with experienced product and engineering leaders
• To work at BrightPlan, you must live and work in the United States and be eligible for employment by any employer in the U.S. You must have a dedicated workspace and reliable internet service

Responsabilidades

• We are looking for aSenior Applied AI Engineerto help design, build, and scale the systems that power AI across the BrightPlan platform
• This role will play an important part in shaping how AI systems evolve within BrightPlan’s product architecture
• This role focuses on developing reliable, scalable infrastructure and frameworks for LLM-powered applications, enabling the broader engineering team to deliver reliable, high-quality AI features
• You will work closely with the CTO to help shape technical decisions around AI architecture, model usage, and system evolution
• This role is ideal for an engineer who enjoys owning complex technical problems and building the systems that make production AI reliable and scalable
• Design and implement scalable AI services and supporting infrastructure that enable AI-powered product capabilities across the platform
• Develop solutions for evaluating and improving LLM output quality
• Build frameworks and tooling that support AI feature development across the engineering team
• Develop and maintain systems that support model tuning, evaluation, and optimization
• Contribute directly to deployment and operational reliability of AI services in production environments
• Optimize AI services for latency, cost efficiency, and reliability
• Partner with the CTO to evaluate emerging AI capabilities and recommend technical approaches for model usage, architecture, and system design
• Provide technical guidance to engineers building AI-powered features and help establish effective development patterns and engineering best practices
• Contribute to technical architecture discussions related to AI systems and platform capabilities
• Contribute meaningfully to establishing reliable systems supporting AI-powered product features within your first 90 days
• Improve the performance, consistency, and reliability of AI-generated outputs
• Enable faster experimentation and iteration for AI product development
• Help establish development patterns and technical practices that enable other engineers to build AI-powered features more effectively
• Demonstrate strong technical leadership and ownership of AI system design and implementation
• Work on practical AI applications deployed in a live fintech product

Benefícios