Responsibilities
- Design, build, and maintain services that power AI-driven applications, ensuring scalability and performance.
- Develop APIs and microservices that facilitate seamless integration between cloud-based AI models and edge devices.
- Optimize data pipelines and storage solutions for real-time AI inference and processing.
- Implement security and privacy best practices for distributed AI systems.
- Work closely with AI researchers, infrastructure engineers, and frontend developers to deliver end-to-end AI-driven solutions.
- Build and optimize an agent orchestration runtime that enables tool use, memory management, and multi-step reasoning across LLMs, APIs, and edge-connected systems.
- Develop robust logging, monitoring, and alerting systems to ensure system reliability.
Requirements
- 10+ years of experience in backend software development, with strong proficiency in Java, C++, or Python.
- Proficient in LLM integration into multi-agent systems with strong understanding of agent orchestration, tool use, and memory/context management.
- Comfortable tinkering with LLMs via prompting and experienced with tools use, task decomposition, and structured outputs.
- Experience building distributed systems, microservices, and cloud-native applications.
- Strong knowledge with building secure, privacy-aware interfaces between models, devices, and external services.
- Familiarity with database management systems (SQL and NoSQL) and data streaming technologies.
- Strong problem-solving skills and ability to work in a fast-paced, agile environment.
Nice to Have
- Experience with AI model deployment and integration into backend services.
- Knowledge of edge computing, networking, and security best practices.
- Exposure to cloud-edge hybrid architectures and distributed AI workloads.
- Familiarity with on-device AI frameworks such as TensorFlow Lite, ONNX Runtime, or CoreML.
