Senior Software Engineer focusing on performance of LLMs and AI workloads on distributed infrastructure. Working with cutting-edge technologies and improving efficiency for enterprise applications.
Responsibilities
Add support for new LLMs, working across the stack from low-level GPU kernels to Kubernetes-based deployments.
Contribute to cutting-edge open-source LLM engines such as vLLM or SGLang to extend their capabilities and performance (e.g. use Python technologies to improve API servers or request schedulers).
Operate closer to the hardware, focusing on building and integrating solutions to boost performance and hardware utilization. For example, improve attention backends like FlashAttention or FlashInfer by contributing to their development and optimization, or by integrating their solutions into vLLM.
Improve LLM performance using advanced algorithmic solutions such as speculative decoding, quantization, or other state-of-the-art techniques. Understand the impact of such techniques in model quality.
Requirements
Expertise in GPU computing, including low-level platforms such as CUDA, ROCm, XLA, PyTorch, Jax, etc.
Background in performance analysis and optimization of AI/HPC workloads (e.g. profiling or theoretical analysis of Flops and bandwidth).
Experience in writing GPU kernels using technologies like CUDA, CUTLASS, Triton.
Strength in Python and C++.
Demonstrated contributions to open-source projects. Contributions to inference engines such as vLLM is a strong plus.
A production-oriented mindset emphasizing robust, scalable code suitable for enterprise-grade applications.
A relentless curiosity about cutting-edge AI technologies combined with a passion for solving complex problems.
Mid - Level Full Stack Developer at Boeing developing cloud - native solutions and AI - driven data analytics. Contributing to software design and deploying complex components in an Agile environment.
Software Engineer II for Disney Streaming services, building systems that power viewer playback. Collaborating with teams to implement scalable backend services for media platforms.
Senior Full Stack Engineer delivering full‑stack JavaScript/TypeScript solutions for AND Digital. Engaging with stakeholders and shaping technical approaches in a hybrid working environment.
Technical Consultant - Full Stack Developer at Daon, focusing on digital identity solutions and integration with existing systems. Collaborating with global teams and supporting mission - critical environments.
Full Stack Developer at Fadami specializing in system integrations and responsive web development. Working with C#, ASP.NET, and various databases in a dynamic, delivery - oriented environment.
Senior Full Stack Developer at Fadami developing scalable solutions and ensuring code quality. Responsible for code reviews and mentoring fellow developers in innovative tech solutions.
Lead Software Engineer in R&D, guiding projects and teams through engineering challenges. Collaborating with stakeholders, architecting software solutions, and leading technical leadership.
Software Engineer implementing microservices and user interfaces for application software at GE Vernova. Collaborating across teams to meet customer requirements and deliver high - quality solutions.
Software Architect developing state - of - the - art Imaging Radar solutions for ADAS and Autonomous Driving at Mobileye. Collaborating in a fast - paced environment to innovate technology in early stages.
Senior Engineering Leader for Permanent Way Engineering at Transport for London, ensuring reliability and safety of railway systems through engineering skills and stakeholder relationships.