Tasks:
- * Build model inference services
- * Build speech-driven AI agents
- * Design end-to-end voice interaction architecture
- * Develop context management and multi-turn dialogue
- * Develop microservices and cloud native deployments
- * Develop real-time voice processing pipelines
- * Implement memory, tool calling, and task planning
- * Implement service governance and observability
- * Optimize high-concurrency AI services
- * Optimize voice interaction latency and stability
Perks/Benefits:
- + Full-time conversion opportunity
Skills/Tech stack required:
[AEC] [AI Agents] [C++] [Cloud Native] [Cloud-Native Deployment] [Computer Networking] [Concurrent Systems] [Data Structures] [Data Structures and Algorithms] [Distributed Systems] [Docker] [Go] [Kubernetes] [Linux] [LLM Inference] [Microservices] [Multimodal AI] [Noise Reduction] [ONNX Runtime] [Operating Systems] [Python] [RAG] [Rust] [SGLang] [Streaming ASR] [Streaming TTS] [TensorRT] [Tool-Calling] [Triton] [VAD] [VLLM]
Educational requirements:
[Bachelor's Degree] [Master's Degree]
Role(s):
[AI Infrastructure Engineer] [AI Infrastructure Engineer Intern] [Engineer Intern] [Infrastructure Engineer Intern] [Intern] [Voice Interaction Engineer Intern]