Software Engineer, ML Inference Platform

About Dialpad Dialpad is the AI platform for customer experience, built to resolve customer problems in real time across voice and digital. Our AI agents learn from your best human agents and improve with every interaction, helping organizations understand their customers, deliver better experiences, increase operational efficiencies, and build a lasting competitive advantage. Unlike legacy systems built to route and answer, or standalone agentic bot vendors built to deflect, Dialpad was built to resolve. Our AI agents and human agents operate on a single platform with shared context, allowing Agentic AI to resolve issues, advance deals, and eliminate busywork through automation while seamlessly handing conversations to humans when needed, with full context preserved. Market-leading brands, including Randstad, Motorola Solutions, Netflix, the San Diego Padres, the Colorado Rockies Baseball Club, and Cal Athletics, trust Dialpad. Dialpad is backed by Andreessen Horowitz, GV, ICONIQ Capital, and T-Mobile. Being a Dialer At Dialpad, AI isn’t just a feature; it’s how our teams do their best work every day. We put powerful AI tools in every employee’s hands so they can move faster, think bigger, and achieve more. We believe every conversation matters. And we’ve built the platform that turns those conversations into insight and action, for our customers and ourselves. We look for people who are intensely curious and hold themselves to a high bar. Our ambition is significant, and achieving it requires a team that operates at the highest level. We seek individuals who embody our core traits: Scrappy, Curious, Optimistic, Persistent, and Empathetic . Your role We are hiring ML Inference Platform Engineers to build the production systems that serve our in-house AI models at scale. This role sits at the intersection of model development, high-performance runtime systems, and cloud infrastructure. You will help turn trained models and emerging AI capabilities into reliable, observable, low-latency production services running on NVIDIA GPUs in GCP. This is not a research role, and it is not a generic MLOps or support role. It is an implementation-heavy systems engineering role focused on the machinery of inference: model serving, runtime optimization, GPU utilization, deployment safety, traffic management, benchmarking, and production reliability. Our mission is to shorten the path from promising model capability to dependable production impact. We build the shared infrastructure, standards, and release pathways that allow models to move from candidate artifacts into scalable, rollback-safe inference services with clear performance, reliability, and cost characteristics. This is a new team, so the systems and interfaces are still being shaped. You will help define how models are packaged, deployed, benchmarked, monitored, compared, and operated across environments. The work is practical, deeply technical, and closely tied to the company’s broader AI strategy. We are not building one-off demos; we are building the inference platform by which a growing AI organization can repeatedly and safely ship real model-backed products. What you’ll do You will design, build, and improve the systems that connect AI capability development to production inference. Depending on your strengths, your work may include: Inference Serving & Runtime Systems: Build and improve model-serving pathways for low-latency, high-throughput, high-availability inference workloads. GPU Infrastructure & Utilization: Operate and optimize containerized workloads on Kubernetes/GCP, with a focus on efficient use of NVIDIA GPUs, memory, storage, and networking. Model Server Integration: Work with model-serving frameworks and runtimes such as vLLM, Triton, TGI, or similar systems, adapting them to internal deployment, observability, and release requirements. Traffic & Release Safety: Enable shadow serving, canary rollouts, staged deployments, candidate-versus-incumbent comparison…