Design, develop, and maintain robust AI/ML infrastructure solutions to support the inference and deployment of large-scale AI models using Kubernetes and Python on popular services such as AWS cloud
Optimization of services to address high performance, latency, and throughput (load) requirements
Understanding sophisticated service requirements and technical constraints of various platforms while implementing solutions to vastly simplify the software stack, accelerating the inference ML models
Experience in building platform features to generalize across multiple customer applications
Collaborate closely with client or customer application teams to build re-usable solutions
Build the infrastructure for developing efficient, reliable, testable services code in a variety of technical stacks
Work closely with partner engineering teams to guide the development process from requirements and design through development, integration, testing, and deployment
Partner closely with various Adobe teams advising on using our technology, investigating bugs, and collaborating on providing new features
Respond to urgent production issues requiring fast resolution and deployment of code fixes/updates
Participate in inventing technology that has an enormous impact across Adobe, writing patents, and participating in an active internal community of software development professionals

Requirements

Bachelor's degree, Master’s degree, or equivalent experience in Computer Science, Engineering, Mathematics, etc. or equivalent practical experience
Firm computer science fundamentals, including design patterns, algorithms, asymptotic complexity, parallelism, and database schema design
Previous experience building, optimizing and operating GPU intensive machine learning workloads in production environments with strong hands-on experience with large-scale GenAI model inference
Exceptional understanding of model serving, orchestration, scaling, GPU resource management
Highly proficient using programming languages such as Go/Python/Rust, Linux environments, k8s, and AWS
Well established distributed computing principles, proven experience building high scale high performance cloud platforms and services
Extensive experience with CI/CD and an in-depth knowledge of containerization and modern deployment strategies & monitoring tools
Works well in a small, collaborative, highly productive team environment across multiple geographies
Excellent verbal and written communication skills
Bonus Qualifications: Experience with GPU-based ML inference services

Benefits

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills & Tools

PythonGoRustKubernetesGPU resource managementCI/CDcontainerizationcloud platformsdesign patternsalgorithms

Soft Skills

collaborationcommunicationproblem-solvingteamworkadaptabilitycreativityleadershipcritical thinkingtime managementattention to detail

Certifications

Bachelor's degreeMaster’s degreeComputer ScienceEngineeringMathematics