Senior Member of Technical Staff: ML Systems and Infrastructure

<div class="content-intro"><p><span style="font-size: 12pt;"><strong>About DevRev</strong></span></p> <p>At DevRev, we're building the future of work with <em>Computer</em> – your AI teammate. Unlike traditional tools, <em>Computer</em> unifies all your data sources, tools, and workflows into a single AI-ready platform, giving employees real-time insights, proactive suggestions, and powerful agentic actions. It extends your existing software with AI-native apps and agents that work alongside your teams and customers – updating workflows, coordinating across teams, and eliminating repetitive work. We call this Team Intelligence: human-AI collaboration that breaks down silos, brings people back together, and frees you to solve bigger problems. Backed by Khosla Ventures and Mayfield with $150M+ raised, DevRev is trusted by global companies across industries.</p></div><p><strong>What You’ll Do:</strong></p> <ul> <li><strong>Architect the Future of AI Infrastructure:</strong> You will design, build, and own the end-to-end platform that supports the entire lifecycle of our ML models—from massive-scale distributed training to ultra-low-latency, highly-available inference.</li> <li><strong>Optimize and Serve Cutting-Edge Models:</strong> You'll implement and scale sophisticated inference stacks for LLMs using frameworks like <strong>vLLM, TensorRT-LLM, or SGLang</strong>. You’ll solve complex challenges in throughput, latency, token streaming, and automated scaling to deliver a seamless user experience.&nbsp;</li> <li><strong>Empower AI Innovation:</strong> You will act as a strategic partner to our AI Research and Data Science teams. You’ll create a seamless developer experience that accelerates their ability to experiment, fine-tune, and deploy groundbreaking models with velocity and confidence.</li> <li><strong>Automate Everything:</strong> You'll develop robust CI/CD/CT (Continuous Training) pipelines using tools like <strong>Argo Workflows, ArgoCD, and GitHub Actions</strong> to automate model validation, deployment, and lifecycle management, ensuring our systems are both agile and rock-solid.</li> </ul> <h3><strong>What are we looking for</strong></h3> <ul> <li><strong>Experience:</strong> 5+ years in infrastructure or software engineering, with at least 2+ years laser-focused on MLOps or ML infrastructure for large-scale distributed systems.</li> <li><strong>Education:</strong> A Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field.</li> <li><strong>Kubernetes &amp; Cloud Native Expertise:</strong> Deep, hands-on expertise with <strong>Kubernetes</strong> in production. You are fluent in the cloud-native ecosystem, including <strong>Helm, ArgoCD, and Argo Workflows</strong>.</li> <li><strong>GPU &amp; Cloud Mastery:</strong> Optimize the platform’s performance and scalability, considering factors such as GPU resource utilization, data ingestion, model training, and deployment.</li> <li><strong>Modern LLM Serving Experience:</strong> Hands-on experience with modern LLM inference serving frameworks (e.g., <strong>vLLM, SGLang, Triton Inference Server, Ray Serve</strong>). You understand the unique challenges of serving generative models.</li> <li><strong>Strong Coder:</strong> Strong programming proficiency in <strong>Python</strong> or <strong>Go</strong>, with experience using ML frameworks like <strong>PyTorch</strong>, <strong>Jax</strong>, <strong>TensorFlow</strong>.</li> <li><strong>Observability Mindset:</strong> A passion for building observable and resilient systems using modern monitoring tools (e.g., Prometheus, Grafana, OpenTelemetry).</li> </ul> <p><strong>We would love to see:</strong></p> <ul> <li>Deep performance optimization skills, including writing <strong>custom inference kernels in CUDA or Triton</strong> to accelerate model performance beyond what off-the-shelf frameworks provide.</li> <li>Experience with model optimization techniques like <strong>quantization, distillation, and speculative decoding</strong>.</li> <li>Exposure to training and serving <strong>multi-modal models</strong> (e.g., text-to-image, vision-language).</li> <li>Knowledge of <strong>AI safety and evaluation frameworks</strong> for monitoring model performance for things like bias, toxicity, and hallucinations.</li> </ul> <p>As part of our hiring process, shortlisted candidates will undergo a Background Verification (BGV). By applying, you consent to sharing personal information required for this process. Any offer made will be subject to successful completion of the BGV.</p><div class="content-conclusion"><p><em>DevRev is an equal opportunity employer and does not discriminate on the basis of race, gender, sexual orientation, gender identity/expression, national origin, disability, age, genetic information, veteran status, marital status, pregnancy or related condition, or any other basis protected by law.</em></p></div>