Senior Site Reliability Engineer, AI Inference

This role is pivotal in advancing F5’s AI capabilities, ensuring enterprise-grade reliability by leveraging hardware acceleration, designing scalable infrastructure, and monitoring system performance.

Key Responsibilities

High-Performance AI Serving

Build and maintain robust inference engines using tools likevLLM,TGI (Text Generation Inference), andNVIDIA Triton, ensuring high performance at scale.

Handle deployment optimizations to deliver low-latency AI serving solutions for multiple business applications.

Hardware Acceleration and Optimization

Profile and optimize models for specialized hardware backends, includingNVIDIA GPUs(CUDA/TensorRT),Apple Silicon (CoreML), and AI accelerators likeTPUsandLPUs.

Collaborate with hardware teams to maximize utilization and performance across various computational environments.

Inference Orchestration and Scalability

Design and implementauto-scaling architecturesfor online (real-time) and batch inference pipelines, leveragingKubernetesfor inference routing and orchestration.

Ensure software solutions are optimized for peak performance during traffic spikes, maintaining reliability and scalability.

Performance Monitoring and Observability

Establish robust observability frameworks to monitorTime to First Token (TTFT), tokens per second, and memory bandwidth utilization against service-level agreements (SLAs).

Build and executeperformance and load testing suitesto identify bottlenecks and ensure consistent reliability at scale.

Technical Requirements

Required Skills:

Programming Languages:Proficiency in programming languages such asPython,C++,Rust, orGolangspecifically for high-performance AI workflows.

Inference Tools:Proven hands-on experience with tools likevLLM,TensorRT,Llama.cpp, andOllamafor inference development and optimization.

Infrastructure Expertise:Strong familiarity with infrastructure technologies, includingDocker,Kubernetes, and cloud platforms such asAWS,GCP, andAzure.

Hardware Optimization Expertise:Comprehensive understanding of GPU and AI hardware, including techniques for profiling and optimizing performance for accelerators like NVIDIA GPUs and TPUs.

Preferred Experience:

Prior experience deployingLarge Language Models (LLMs)with advanced techniques likeSpeculative DecodingorPagedAttention.

Contributions toopen-source inference librariesor hardware-level kernel development (e.g., CUDA, Triton kernels).

Background inMLOpsorSREroles focused onhigh-performance AI endpointsand reliability during demand surges.

Proficiency in designing scalable solutions for high-throughput inference environments optimized for traffic bursts.

Success Metrics (KPIs):

Latency Reduction:Continuously improve inference latency metrics, ensuring minimalTime to First Token (TTFT)and maximum tokens per second.

Cost Efficiency:Achieve lower "Cost per 1K Tokens" through better resource utilization and hardware optimization.

Scalability:Maintain system stability and reliability duringtraffic spikes, ensuring performance consistency across environments.

Throughput Maximization:Deploy models optimized for peak hardware usage and maximized process throughput.

Why Join F5?

F5 empowers you to push boundaries inAI optimizationandhigh-performance engineering. Joining our team means:

Collaborating with cutting-edge technologies and hardware solutions to support real-time AI applications.

Advancing your career in a fast-paced, multidisciplinary environment focused on innovation, scalability, and problem-solving.

Driving transformative projects that deliver real-time AI reliability to global customers while maintaining cost and efficiency standards.

Working on advancedMLOpssolutionsthat seamlessly scale enterprise AI systems and shape the future of intelligent deployment.

What Success Looks Like:

As anAI Inference Engineerat F5, success is measured by your ability to:

Combine technical expertise and problem-solving skills to deliver low-latency, scalable, and high-performing AI prediction systems.

Collaborate efficiently across cross-functional teams, participating in knowledge sharing and system refinement.

Demonstrate initiative by driving optimizations across hardware, tools, and orchestration processes, balancing immediate solutions with long-term architectural goals.

Translatecomplex AI and inference workflows into practical solutions that align with F5's strategic objectives.

The Job Description is intended to be a general representation of the responsibilities and requirements of the job. However, the description may not be all-inclusive, and responsibilities and requirements are subject to change.

Please note that F5 only contacts candidates through F5 email address (ending with @f5.com) or auto email notification from Workday (ending with f5.com or@myworkday.com).

Equal Employment Opportunity

It is the policy of F5 to provide equal employment opportunities to all employees and employment applicants without regard to unlawful considerations of race, religion, color, national origin, sex, sexual orientation, gender identity or expression, age, sensory, physical, or mental disability, marital status, veteran or military status, genetic information, or any other classification protected by applicable local, state, or federal laws. This policy applies to all aspects of employment, including, but not limited to, hiring, job assignment, compensation, promotion, benefits, training, discipline, and termination. F5 offers a variety of reasonable accommodations for candidates. Requesting an accommodation is completely voluntary. F5 will assess the need for accommodations in the application process separately from those that may be needed to perform the job. Request by contacting accommodations@f5.com.