Principal AI Engineer

OUR VALUES

• Best Life - We believe great work begins with great people. That’s why our culture is built on respect, trust, and belonging. We create an inclusive environment where every team member can bring their authentic self to work—because diverse perspectives drive innovation and meaningful impact.
• Growth Mindset - We are doers, thinkers, and dreamers. At ABC Fitness, your growth is our investment. Through continuous learning, mentorship, and professional development opportunities, we empower you to reach new heights—personally and professionally.
• One Team - From day one, you’ll be part of a team that collaborates, celebrates, and cares. We move fast, support one another, and have fun along the way. Because when you thrive, we all thrive.

• Work cross-functionally with Product/Design to translate ambiguous problems into measurable outcomes and shippable iterations. Lead the estimation of work at the quarterly level. Provide alternative solutions and negotiate with Product Management.
• Build and ship LLM-powered product capabilities end-to-end: APIs, orchestration logic, integrations, and production rollouts
• Design and implement agentic workflows (tool use, planners/routers, multi-step reasoning, handoffs, memory/state management) using modern orchestration frameworks (e.g., Lang Chain/Lang Graph-style)
• Develop strong prompting + context engineering practices, including prompt versioning and experimentation (e.g., A/B testing approaches)
• Build evaluation harnesses for LLM apps: curated test sets, automated checks, offline/online metrics, human review loops, and regression gates for changes
• Collaborate with platform/infra teams to deploy on AWS, ensuring reliability, security, scalability, latency, and cost controls
• Be an active participant in the day-to-day agile activities of the team including sprint planning, daily standups, sprint reviews, and retrospectives
• Instrument systems for observability (quality, latency, token/cost, errors) and create feedback loops to improve model+system behavior over time
• Develop high quality solutions; leads the creation of new standards, patterns, and best practices
• Write architecture & design documentation for new products, systems, and patterns
• Review the work of teammates to ensure quality and adherence to system architecture and best practices; identify where new designs will require architectural changes
• Mentor junior developers to grow their skills
• Troubleshoot and resolve complex and highly escalated customer/QA found issues in a timely manner
• Experiment with new technologies that can enhance our tech stack. Provide new technology insights to remainder of development team.
• Lead the implementation of development process improvements that add efficiency for the entire development team
• Participate in build vs. buy analysis and complex decision making
• Conduct regular, self-guided study to stay current on new and existing technologies
• Participate in the hiring process and technical screens with an aim of attracting and hiring the very best engineers; work to expand the onboarding efficacy and vision
• May represent the team through presentations to other company departments and customers

• Engineering or Comp Science degree or equivalent work experience
• 9+ years of professional experience in software engineering, applied ML, data science engineering, or AI product engineering
• Strong Python skills, experience building backend services (e.g. Flask/FastAPI) and integrating with REST APIs
• Some applied ML / data science experience (e.g., experiments, model evaluation, error analysis, feature work, or shipping ML-informed product changes), even if your recent focus has shifted toward software/AI engineering
• Practical understanding of LLMs/SLMs and how they behave in production (hallucinations, prompt sensitivity, latency/cost tradeoffs)
• Hands-on experience building LLM applications (RAG, tool use, agents, workflow orchestration), with the ability to demonstrate end-to-end ownership from prototype to production, measurement, iteration
• Experience with cloud infrastructure (e.g. AWS) and shipping production workloads (containers, deployments, monitoring)
• Strong…