You will scale and optimize a generative AI conversation engine to support hundreds of millions of users across multiple chat channels.
Responsibilities
- Design scalable API abstractions for clients including MS Teams, Slack, and Web.
- Optimize the dialog engine for low latency, minimal memory footprint, and real-time multilingual translation.
- Construct product infrastructure and user interfaces enabling engineers to customize and optimize generative AI models.
- Implement logging, tracing, and automated metrics frameworks to provide visibility into product performance.
- Collaborate with ML engineers and product teams to iterate on new features and scalability initiatives.
Required Skills
- 5+ years of experience in software development and building scalable systems.
- Strong foundation in Computer Science principles.
- Expertise in clean, modular, and scalable API design.
- Experience designing and implementing user interfaces.
- Proficiency in identifying and resolving latency bottlenecks, race conditions, and throughput limitations.
- Working knowledge of tracing, logging, and metrics frameworks.
- Ability to research requirements independently and develop technical solutions.
Preferred Skills
- Bachelor's degree or higher in Computer Science or a related field.