Senior II Software Engineer
Akamai Technologies
⚲ Kraków, Prądnik Biały
Wymagania
- TensorRT
- vLLM
- TorchServe
- Triton
Opis stanowiska
Nasze wymagania: Possess 6+ of software engineering experience with expertise in distributed systems, cloud services, and platform engineering. Demonstrate hands-on experience with AI inference, model serving, or LLM deployment with working knowledge of inference frameworks (TensorRT, vLLM, TorchServe, Triton). Demonstrate expertise in cloud-native architectures, encompassing containerization and orchestration technologies such as Kubernetes and Docker. Have experience building scalable, high-performance systems with modern DevOps practices, CI/CD pipelines, and infrastructure-as-code. Exhibit technical leadership by mentoring, promoting code quality, and driving effective solutions for complex challenges. Have knowledge of observability, monitoring, and debugging distributed systems. Show familiarity with GPU infrastructure and hardware acceleration. O projekcie: As a Senior II Software Engineer, responsibilities include designing and implementing key components of a globally distributed AI inference platform. Work involves building and optimizing systems that deliver OpenAI-compatible endpoints while managing inference workloads across regions. This role demands proficiency in AI/ML systems, effective problem-solving abilities, and skill in delivering dependable software within a complex distributed infrastructure. Zakres obowiązków: Designing and implementing critical platform components for Akamai Inference Cloud, ensuring performance, scalability, and reliability. Driving technical decisions for your domain, selecting appropriate tools, frameworks, and approaches for AI inference workloads. Supporting other engineers through code reviews, design discussions, and day-to-day technical collaboration. Implementing and optimizing containerized AI workloads with hardware-specific optimizations and integrating inference frameworks at scale. Collaborating across teams to define technical requirements, contribute to platform standards, and ensure operational excellence.