About the job
Join our team as a Senior Machine Learning Services Engineer and help bring cutting-edge AI and Generative AI features to production. Collaborate with top engineers to design, build, and optimize scalable ML cloud services powering Adobe’s flagship creative products. Shape the future of AI innovation in a hands-on, impactful role.
Responsibilities
Design, build, and operate backend cloud services that power ML and Generative AI features across multiple Adobe products; Build an agentic end to end pipeline for tech transfer modernization; Architect and optimize GPU-accelerated ML inference pipelines for scalability, cost efficiency, and reliability in production; Optimize ML models for production inference, including techniques such as quantization, pruning, graph optimization, batching, and hardware-aware tuning to improve latency, throughput, and cost; Analyze and improve performance, quality, stability, and throughput of end-to-end AI workflows; Lead the integration of new ML models into production systems, including model validation, regression testing, and quality evaluation; Build and maintain CI/CD pipelines supporting a suite of ML-backed microservices; Collaborate closely with Research, Product, and Engineering partners to productionize new ML capabilities; Ensure services meet production standards for observability, monitoring, logging, and incident response; Participate in on-call and production support, contributing to a culture of operational excellence
Qualifications
Minimum
5+ years of experience building, optimizing, and operating ML systems in production, including GPU-based workloads; Proven experience designing large-scale, reliable cloud services with strong performance and availability requirements; Strong background in model serving and inference optimization, including techniques for conversion, compression, and orchestration; Hands-on experience with computer vision and/or generative models, such as GANs, diffusion models, CLIP, or MLLMs; Expertise in building agents for workflow automation and orchestration; Proficiency with core technologies such as: Python, PyTorch, TensorFlow; NVIDIA Triton, TorchServe, ONNX, AIT, AOT, CUDA; Docker, Kubernetes, AWS; Solid understanding of GPU systems, drivers, and deployment considerations in cloud environments; Ability to work independently on complex systems while collaborating effectively across teams
Preferred
No preferred qualifications listed.