Member of Technical Staff (Software Engineer, Multimodal)
San Francisco • FullTime
Posted 17d ago
Remote Work Policy
On-site
Employment Type
FullTime
Categories
Applied AI Engineer
About the job
Perplexity is seeking builders to define the future of human-AI interaction, moving beyond text and touch into real-time voice and vision. The Multimodal team is at the forefront of this, developing the experiences and infrastructure that enable AI to understand and respond through speech and sight. As a backend engineer on this team, you will be instrumental in designing and scaling the distributed systems that handle live voice sessions, driving innovation at the intersection of voice, vision, and AI agents. This role offers the opportunity to own problems end-to-end, from initial concept to production launch, working with cutting-edge technology in a fast-paced, entrepreneurial environment.
Responsibilities
- Design, build, and scale the backend session-worker architecture for real-time voice, including durable workers, provider routing, and stateful streaming over gRPC.
- Own distributed systems challenges end-to-end, such as session lifecycle management, crash recovery, reconnection, multi-region deployment, and graceful degradation under load.
- Build provider-agnostic streaming protocols from the backend to the Rust SDK for voice experiences across all client platforms.
- Drive new products and initiatives in voice and multimodal AI, from problem definition and technical design through implementation and launch.
- Develop the orchestration layer for live voice models to delegate tasks to tools, agents, and long-running processes safely and at scale.
- Collaborate closely with SDK, client, infrastructure, and model teams, working across the full stack as needed.
Requirements
- 4+ years of professional software engineering experience in backend or distributed systems.
- Strong experience with Rust, Python, or Go.
- Experience designing and operating production distributed systems, including streaming RPC (gRPC or similar), stateful services, message-driven architectures, and failure recovery.
- Solid understanding of cloud infrastructure, including deploying, scaling, and operating services on AWS or equivalent.
- Strong product judgment and ability to translate user problems into effective technical solutions.
- Genuine interest in AI products and a willingness to learn quickly.