11 hours ago
Base Salary
$146k - $264k/yr
Responsibilities
- Lead the design and implementation of scalable, reliable components for Akamai Inference Cloud.
- Drive technical decisions involving tools, frameworks, and approaches for AI inference workloads.
- Implement and optimize containerized AI workloads with hardware-specific optimizations and integrate inference frameworks at scale.
- Mentor engineers through code reviews, design discussions, and technical problem-solving.
- Collaborate across teams on technical requirements and platform standards while ensuring operational excellence.
Requirements
- Eight years of relevant experience and a bachelor's degree or equivalent.
- Proficiency in distributed systems, cloud services, and platform engineering.
- Hands-on experience with AI inference, model serving, or LLM deployment and working knowledge of TensorRT, vLLM, TorchServe, and Triton.
- Experience with Kubernetes, Docker, and cloud-native architectures.
- Experience building scalable, high-performance systems using modern DevOps practices, CI/CD pipelines, and infrastructure-as-code.
- Technical leadership experience including mentoring, code quality advocacy, and driving solutions to complex problems.
- Familiarity with REST and gRPC API design and development, GPU infrastructure, hardware acceleration, observability, monitoring, and debugging distributed systems.
Benefits
- Flexible work arrangement allowing employees to work from home, in an office, or in a combination of both.
- Healthcare, 401(k) savings plan, company holidays, PTO, sick time, parental leave, and an employee assistance program focused on mental and financial wellness.
- Potential annual bonus or incentive compensation, equity awards, and an Employee Stock Purchase Plan; eligibility requirements apply.
Tech Stack
Categories
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.