Senior Software Engineer, Machine Learning Infrastructure - Generative AI
Core
Design and architect production infrastructure for DoorDash's GenAI platform, enabling real-time GPU serving, high-throughput batch inference, and fine-tuning of open-weight LLMs and VLMs for internal automation and product teams.
Role type
Senior IC machine learning infrastructure engineer (Generative AI)
Builds
Open-weights model platform spanning inference, fine-tuning, GPU autoscaling, and observability for DoorDash, Wolt, and Deliveroo
Domain
Generative AI, Large Language Models (LLMs), GPU Infrastructure
Deliverable
production ML models
Required skills
Python, distributed systems, LLM inference, model fine-tuning (SFT/DPO/LoRA), GPU autoscaling, system observability, technical leadership, AI coding tools
Preferred skills
LLM inference engines (vLLM, SGLang, TensorRT-LLM), distributed fine-tuning pipelines, GPU performance optimization (KV-cache, quantization), Kubernetes, cloud infrastructure (AWS/GCP), AI agents
Technologies
Python, vLLM, SGLang, TensorRT-LLM, Kubernetes, AWS, GCP, Modal
Responsibilities
Lead design of infrastructure moving GenAI from prototype to production; Own and evolve the open-weights serving stack; Architect scalable systems for model serving and fine-tuning; Push cost and latency frontiers for GPU inference; Build platforms supporting rapid experimentation with production standards; Partner with ML engineers and data scientists to create reusable platform primitives; Set technical direction for emerging AI techniques like RLHF and agent optimization
Seniority
Senior, hands-on IC