Job Summary At Red Hat we believe the future of AI is open and we are on a mission to bring the power of open-source LLMs and vLLM to every enterprise. Red Hat AI Inference team accelerates AI for the enterprise and brings operational simplicity to GenAI deployments. As leading developers, maintainers of the vLLM project, and inventors of state-of-the-art techniques for model quantization and sparsification, our team provides a stable platform for enterprises to build, optimize, and scale LLM deployments. As a Senior Machine Learning Engineer focused on model optimization algorithms, you will work closely with our product and research teams to develop SOTA deep learning software. You will collaborate with our technical and research teams to develop LLM training and deployment pipelines, implement model compression algorithms, and productize deep learning research. If you are someone who wants to contribute to solving challenging technical problems at the forefront of deep learning in the open source way, this is the role for you. Join us in shaping the future of AI! What you will do - Contribute to the design, development, and testing of various inference optimization algorithms in the vLLM , and related projects, such as llm-d. - Create and manage inference serving deployment pipelines - Benchmark, profile, and evaluate different parallelizations, quantization and sparsification approaches to determine the best performance for specific hardware and models - Stay up-to-date with the latest advancements in the open source LLM model architecture, LLM Inference parallelizations/optimizations techniques, and quantization research - Stay up-to-date of latest CPU and GPU hardware architecture and features to boost AI inference performance - Give thoughtful and prompt code reviews - Continuous collaboration with internal and external open source comitters and contributors while contributing to vLLM and related projects ​ What you will bring - Strong understanding of machine learning and deep learning fundamentals with experience in one or more of LLM Inference Optimizations, Computer Vision, NLP, and reinforcement learning - Experience with tensor math libraries such as PyTorch and NumPy - Strong programming skills with proven experience implementing Python based machine learning solutions - Ability to develop and implement research ideas and algorithms - Experience with mathematical software, especially linear algebra - Understanding of Linear Algebra, Gradients, Probability, and Graph Theory - BS, or MS, or PhD in computer science or computer engineering or a related field. #LI-MD2 #AI-HIRING About Red Hat Red Hat is the world’s leading provider of enterprise open source software solutions, using a community-powered approach to deliver high-performing Linux, cloud, container, and Kubernetes technologies. Spread across 40+ countries, our associates work flexibly across work environments, from in-office, to office-flex, to fully remote, depending on the requirements of their role. Red Hatters are encouraged to bring their best ideas, no matter their title or tenure. We're a leader in open source because of our open and inclusive environment. We hire creative, passionate people ready to contribute their ideas, help solve complex problems, and make an impact. Inclusion at Red Hat Red Hat’s culture is built on the open source principles of transparency, collaboration, and inclusion, where the best ideas can come from anywhere and anyone. When this is realized, it empowers people from different backgrounds, perspectives, and experiences to come together to share ideas, challenge the status quo, and drive innovation. Our aspiration is that everyone experiences this culture with equal opportunity and access, and that all voices are not only heard but also celebrated. We hope you will join our celebration, and we welcome and encourage applicants from all the beautiful dimensions that compose our global village. Equal Opportunity Policy (EEO) Red Hat is proud to be an equal opportunity workplace and an affirmative action employer. We review applications for employment without regard to their race, color, religion, sex, sexual orientation, gender identity, national origin, ancestry, citizenship, age, veteran status, genetic information, physical or mental disability, medical condition, marital status, or any other basis prohibited by law. Red Hat does not seek or accept unsolicited resumes or CVs from recruitment agencies. We are not responsible for, and will not pay, any fees, commissions, or any other payment related to unsolicited resumes or CVs except as required in a written contract between Red Hat and the recruitment agency or party requesting payment of a fee. Red Hat supports individuals with disabilities and provides reasonable accommodations to job applicants. If you need assistance completing our online job application, email application-assistance@redhat.com. General inquiries, such as those regarding the status of a job application, will not receive a reply.

Role Description Raft is building mission-critical AI and data platforms for the Department of Defense (DoD). Our systems ingest and process massive volumes of real-time data from hundreds of sensors and operational sources, transform that data into usable intelligence, and deliver it to operators through mission applications and common operational pictures that support time-sensitive decision-making. Our platform operates at scale, processing billions of events per day with low-latency data pipelines and cloud-native infrastructure. As Raft expands its AI capabilities, we are investing in a more mature end-to-end machine learning platform to support model development, evaluation, deployment, monitoring, and lifecycle management across both cloud and constrained operational environments. In this role, you will help design, deploy, and mature Raft’s ML platform and MLOps infrastructure. You will work across Kubernetes-based deployment environments, GPU-enabled infrastructure, model serving systems, CI/CD pipelines, and secure production operations to enable rapid and reliable delivery of machine learning capabilities. This role is ideal for someone who understands both the infrastructure needed to run ML systems in production and the practical needs of ML engineers building and deploying models. What you’ll do: - Design, build, and maintain secure, scalable MLOps infrastructure and deployment pipelines for production ML systems - Help mature Raft’s internal ML platform and model lifecycle capabilities, including model packaging, registry/catalog workflows, deployment, monitoring, and operational support - Deploy and manage machine learning workloads on Kubernetes, including GPU-enabled clusters - Support model serving and inference infrastructure for a range of ML use cases, including traditional ML, computer vision, speech/audio, and LLM-based systems - Build and maintain CI/CD workflows for ML services, model artifacts, and platform components - Partner closely with ML engineers, software engineers, and product teams to move models from experimentation to reliable operational deployment - Improve observability, reliability, security, and maintainability across ML infrastructure and services - Help evaluate and standardize runtime patterns, serving frameworks, and deployment architectures for production ML workloads - Contribute to infrastructure decisions across edge, on-prem, and cloud-hosted deployment environments - Support compliance-driven deployment practices and secure software supply chain requirements in defense environments - Get hands-on with customers at the most forward-leaning places in the Department of War Qualifications - 7+ years of relevant hands-on experience in software engineering, platform engineering, DevOps, MLOps, or related technical roles - 5+ years of experience with Docker and Kubernetes in production environments - 5+ years of experience supporting enterprise cloud infrastructure or applications in AWS, Azure, or similar environments - Strong experience provisioning, operating, and troubleshooting Kubernetes clusters in production - Experience building and maintaining machine learning platforms, infrastructure, or pipelines used by engineering or data science teams - Practical experience deploying machine learning workloads on Kubernetes - Experience managing clusters or workloads that use GPUs - Strong understanding of Helm and Kubernetes deployment patterns - Strong scripting or programming skills, preferably in Python - Experience with modern software engineering practices including Git, CI/CD, DevOps, and Agile/Scrum workflows - Strong troubleshooting, systems thinking, and communication skills - Ability to work independently and collaboratively in a fast-moving environment - Ability to obtain and maintain a Top Secret clearance - Ability to obtain Security+ certification within the first 90 days of employment Highly preferred: - Experience with ML model serving and inference platforms such as Triton Inference Server, KServe, Ray Serve, vLLM, or similar technologies - Experience with secure and compliant deployment practices in regulated or government environments - Experience with Kubernetes-based ML platforms such as Kubeflow - Familiarity with service mesh technologies such as Istio - Experience provisioning and debugging complex CI/CD systems - Experience with infrastructure as code tools such as Terraform - Familiarity with software supply chain security, container hardening, vulnerability management, and runtime scanning - Experience supporting ML systems across multiple deployment environments, including cloud, on-prem, and edge - Background working with machine learning engineers on model training, evaluation, packaging, and release workflows - Familiarity with storage and artifact systems used in ML platforms, such as S3-compatible object stores, registries, and metadata/catalog system What success looks like: - You help Raft stand up a more mature and repeatable ML platform for deploying and managing models in production - ML engineers can move faster because deployment, serving, and platform workflows are clearer, more reliable, and easier to use - Model deployments become more secure, observable, and supportable across real-world mission environments - The organization gains stronger infrastructure for model lifecycle management, including deployment standards, runtime patterns, and platform ownership Clearance Requirements: - Ability to obtain and maintain a Top Secret clearance Work Type: - Remote in DMV; McLean, VA; Boston, MA; San Antonio, TX; Colorado Springs, CO; Tampa, FL; Honolulu, HI - May require up to 40% travel Salary Range: $150,000.00 - $200,000.00 What we will offer you: - Highly competitive salary - Fully covered healthcare, dental, and vision coverage - 401(k) and company match - Take as you need PTO + 11 paid holidays - Education & training benefits - Annual budget for your tech/gadgets needs - Monthly box of yummy snacks to eat while doing meaningful work - Remote, hybrid, and flexible work options - Team off-site in fun places! - Generous Referral Bonuses - And More!

• Design, build, and iterate on machine learning models and LLM-based systems that power critical decisions across fraud, compliance, growth, and operations • Work with messy, real-world data to identify signals, build features, and continuously improve model performance • Make practical tradeoffs between model performance, interpretability, and operational cost • Partner closely with product and operations to identify and solve problems that directly impact experience of hundreds of thousands of clients • Contribute to backend systems and data pipelines that support model training and inference (without being primarily an infrastructure role) • Write high-quality, tested code and participate in code reviews • Take long-term ownership of critical systems as River scales

• You will develop and iterate on fraud prediction models using a mix of approaches for tabular and behavioral data • You will build and scale feature pipelines and training datasets from proprietary and third-party signals, partnering with data and platform teams when needed. • You will prototype new modeling ideas and features, run offline experiments, and drive the best-performing approaches into production with appropriate risk controls. • You will help productionize models: integrate into batch and/or real-time decision systems, and improve reliability, latency, and operational robustness. • You will instrument and monitor model and data health, and help define retraining/backtesting workflows as fraud patterns evolve. • You will collaborate across Engineering, Fraud Analytics, Product, and ML Platform to define requirements, evaluate tradeoffs, and communicate results clearly to both technical and non-technical audiences.