1 day ago
Remote, Poland or Kraków, PolandSenior
Responsibilities
- Develop and maintain prompt processing and tokenization pipelines for inference requests.
- Implement request routing, scheduling, and batching logic for concurrent inference workloads.
- Integrate new model architectures and serving backends into the runtime framework.
- Write tested and documented code and participate in code reviews.
- Support operational readiness through monitoring, debugging, profiling, and performance analysis of runtime components.
Requirements
- Relevant software engineering experience and a bachelor’s degree or equivalent in Computer Science or a related field.
- Proficiency in Python and at least one systems programming language such as C++, Go, or Rust.
- Understanding of natural language processing concepts including tokenization, encoding, and text processing pipelines.
- Familiarity with AI inference, model serving, or LLM deployment and frameworks including TensorRT, vLLM, TorchServe, or Triton.
- Experience building high-throughput, low-latency data processing systems or services.
- Familiarity with Linux systems, containerized environments, and profiling or debugging tools.
- Willingness to learn and grow in AI inference and model serving.
Benefits
- Akamai provides health, well-being, financial, and broader life benefits.
- FlexBase supports working from home, in an office, or through a combination of both.
- Remote position based in Poland.
About Akamai
Akamai builds content delivery, cloud security, and edge compute services for enterprises that run consumer and business web, API, and video workloads. The public company (NASDAQ: AKAM), founded in 1998 and headquartered in Cambridge, MA, operates a global CDN and security platform and sells via subscriptions and usage-based services. It expanded into cloud infrastructure by acquiring Linode in 2022, offering IaaS and managed Kubernetes.
