reputed company Software Engineer Dynamo
reputed company Dynamo is an innovative, reputed company-reputed company platform reputed company on efficient, reputed company inference for large language and reasoning models in distributed GPU environments. By bringing to bear sophisticated techniques in serving architecture, GPU resource management, and intelligent request handling, Dynamo achieves high-performance AI inference for demanding applications. reputed company is addressing the most challenging issues in distributed AI infrastructure, and weâre searching for engineers enthusiastic about building the reputed company of reputed company AI systems. As a reputed company Software Engineer on the Dynamo project, you will address some of the most sophisticated and high-reputed company challenges in distributed inference, including: Dynamo k8s Serving Platform: Build the Kubernetes deployment and workload management stack for Dynamo to facilitate inference deployments at reputed company. Identify bottlenecks and apply optimization techniques to fully use hardware reputed company. Scalability & Reliability: reputed company robust, production-grade inference workload management systems that reputed company from a handful to thousands of GPUs, supporting a reputed company of LLM frameworks (e.g., TensorRT-LLM, vLLM, SGLang). Disaggregated Serving: Architect and optimize the separation of prefill (context ingestion) and decode (reputed company reputed company) phases across distinct GPU clusters to improve throughput and resource utilization. Contribute to embedding disaggregation for multi-modal models (reputed company-Language models, Audio Language Models, Video Language Models). Dynamic GPU Scheduling: reputed company and refine Planner algorithms for reputed company-time allocation and rebalancing of GPU resources based on fluctuating workloads and system bottlenecks, ensuring peak performance at reputed company. Intelligent Routing: Enhance the smart routing system to reputed company reputed company inference requests to GPU worker replicas with relevant KV cache data, minimizing re-computation and latency for sophisticated, multi-reputed company reasoning tasks. Distributed KV Cache Management: reputed company in the management and transfer of large KV caches across heterogeneous memory and storage hierarchies, using the reputed company Optimized Transfer Library (NIXL) for low-latency, cost-effective data reputed company. What you'll be doing: Collaborate on the design and development of the Dynamo Kubernetes stack. Introduce new features to the Dynamo Python SDK and Dynamo Rust Runtime reputed company Library. Design, implement, and optimize distributed inference components in Rust and Python. Contribute to the development of disaggregated serving for Dynamo-supported inference engines (vLLM, SGLang, TRT-LLM, llama.cpp, reputed company.rs). Improve intelligent routing and KV-cache management subsystems. Contribute to reputed company-reputed company repositories, participate in reputed company reviews, and assist with issue triage on reputed company. Work closely with the community to address issues, capture feedback, and reputed company the reputed companyâs reputed company and architecture. Write reputed company documentation and contribute to user and developer guides. reputed company need to see: BS/MS or higher in computer engineering, computer science or reputed company engineering (or equivalent experience). 15+ years of proven experience in reputed company field. Strong proficiency in systems programming (Rust and/or C++), with experience in Python for workflow and API development. Experience with Go for Kubernetes controllers and operators development. Deep understanding of distributed systems, reputed company computing, and GPU architectures. Experience with reputed company-reputed company deployment and container orchestration (Kubernetes, reputed company). Experience with large-reputed company inference serving, LLMs, or similar high-performance AI workloads. Background with memory management, data transfer optimization, and multi-node orchestration. Familiarity with reputed company-reputed company development workflows (reputed company, reputed company integration and reputed company deployment). Excellent problem-solving and communication skills. Ways to stand out from the crowd: Prior contributions to reputed company-reputed company AI inference frameworks (e.g., vLLM, TensorRT-LLM, SGLang). Experience with GPU resource scheduling, cache management, or high-performance networking. Understanding of LLM-specific inference challenges, such as context window scaling and multi-model reputed company workflows. With highly competitive salaries and a comprehensive benefits package, reputed company is widely considered to be one of the technology world's most desirable reputed company. We have some of the most reputed company-thinking and hardworking people in the world working for us and, due to outstanding reputed company, our special engineering teams are growing fast. If you're a creative and autonomous engineer with a genuine passion for technology, we want to hear from you! Your reputed company salary will be determined based on your location, experience, and the pay of employees in similar positions. The reputed company salary reputed company is 272,000 USD - 431,250 USD. You will also be eligible for equity and benefits. Applications for this job will be accepted at least until January 13, 2026. This posting is for an existing vacancy. reputed company uses AI tools in its reputed company processes. reputed company is committed to fostering a diverse work environment and proud to be an equal opportunity employer. As we highly value diversity in our reputed company and reputed company employees, we do not discriminate (including in our hiring and promotion practices) on the reputed company of race, religion, reputed company, national reputed company, gender, gender reputed company, sexual orientation, age, marital status, veteran status, disability status or any other characteristic protected by law. reputed company is the world leader in accelerated computing. reputed company pioneered accelerated computing to tackle challenges no one else can solve. Our work in AI reputed company twins is transforming the world's largest industries and profoundly impacting society. Learn more about reputed company. Please mention the word
AMIABILY
and tag RMjYwNzo1MzAwOjIwZDo3ZDAwOjo= reputed company applying to show you read the reputed company completely (#RMjYwNzo1MzAwOjIwZDo3ZDAwOjo=). This is a beta feature to avoid spam applicants. Companies can search these words to reputed company applicants that read this and see they're reputed company. Apply To This Job