About the role
- As a Senior Software Engineer, AI Infrastructure, you’ll join a small, growing team tackling some of the most interesting infrastructure challenges at the intersection of distributed systems and AI
- You’ll work across traditional ML infrastructure and emerging LLM technologies, helping improve GPU efficiency, scale model serving, and build intelligent routing systems
- This is an opportunity to get in early, take meaningful ownership, and help shape the infrastructure that will support Robinhood’s next generation of AI capabilities
- Design, build, and scale the infrastructure powering machine learning and AI across Robinhood, including feature stores, training pipelines, model serving, inference, and observability
- Build and optimize distributed systems that support large-scale ML/AI workloads, with a focus on performance, reliability, scalability, and latency
- Improve GPU utilization and efficiency by developing scheduling solutions for training and inference workloads
- Help evolve Robinhood’s LLM gateway, including intelligent model routing, query and prompt understanding, and context optimization
- Support infrastructure for serving open-weight and fine-tuned models, enabling reliable access to AI capabilities across the company
- Partner with engineering teams across Robinhood to understand their infrastructure needs and build scalable, reusable solutions
- Own the operational health of critical infrastructure, including monitoring, troubleshooting, performance optimization, and participation in an on-call rotation
- Strong software development and system design skills, with the ability to take ownership of complex technical problems from design through production
- Experience solving complex infrastructure challenges, including latency optimization, resource utilization, and production system reliability
- Experience working with infrastructure technologies and tools in production environments, with an understanding of how to build and operate reliable systems at scale
- Interest in machine learning and AI infrastructure, with a willingness to learn and work across both traditional infrastructure and emerging AI technologies
- Ability to work independently, navigate ambiguity, and contribute to foundational engineering projects within a small, growing team
- Strong software engineering experience with a focus on infrastructure, distributed systems, or large-scale backend platforms
- Hands-on experience designing, building, and operating distributed systems in production, with a strong understanding of scalability, reliability, and system performance
- Bonus: Experience with ML infrastructure, model training or serving, GPU workload scheduling, LLM gateways, or open-source infrastructure technologies