Senior Software Engineer (Machine Learning Infrastructure - Generative AI)

Location: San Francisco, Sunnyvale, California, or Seattle, Washington, United States

Base salary: $137,100–$201,600, $167,800–$246,800, or $203,500–$299,300 per year, depending on level, location, and qualifications. Equity grants may also be available.

Company

hirify.global is a technology and delivery platform whose Machine Learning Platform team develops shared infrastructure for AI-powered products across hirify.global, Wolt, and Deliveroo.

What you will do

• Design and lead infrastructure for real-time GPU serving, high-throughput batch inference, and open-weight model fine-tuning.
• Set technical direction across inference engines, training pipelines, GPU autoscaling, backend services, observability, and cost attribution.
• Improve GPU inference cost, latency, throughput, utilization, reliability, and fallback behavior for production workloads.
• Build platform capabilities that support experimentation while meeting production standards for monitoring, SLOs, playbooks, and operational excellence.
• Partner with ML engineers, product engineers, data scientists, and platform teams across hirify.global, Wolt, and Deliveroo.
• Mentor engineers and guide future platform work in areas such as RLHF, RLVR, agent optimization, and other post-training techniques.

Requirements

• Bachelor’s, master’s, or doctoral degree in computer science or equivalent experience.
• At least 6 years of industry software engineering experience with strong backend fundamentals, especially Python and distributed systems.
• Experience designing, owning, and operating production services, APIs, data pipelines, or ML infrastructure at scale.
• Hands-on production experience with LLM inference and/or fine-tuning of open-weight models, including serving, batching, autoscaling, GPU utilization, SFT, DPO, or LoRA.
• Experience with observability, debugging, reliability, incident response, and performance or cost optimization.
• Technical leadership experience, including ambiguous system design, mentoring, and using AI coding tools throughout the software development lifecycle.

Nice to have

• Experience with vLLM, SGLang, TensorRT-LLM, distributed fine-tuning, GPU performance optimization, quantization, or multi-node inference.
• Experience with Kubernetes, AWS, GCP, serverless or elastic GPU platforms, and high-throughput batch systems.
• Experience with LLM gateways, model routing, vendor abstraction, developer platforms, AI agents, MCP servers, evaluation systems, RAG, search, or vector databases.

Culture & Benefits

• High-impact work on a small, specialized GenAI infrastructure team.
• Comprehensive benefits for regular employees, including medical, dental, vision, disability, and life insurance.
• 401(k) plan with employer matching, paid parental leave, paid time off, paid sick leave, and 11 paid holidays.
• Wellness, commuter, family-forming, and mental health benefits.
• Flexible paid time off for salaried employees and opportunities for equity grants.

Hiring process

• Recruiting is supported by Gem, an automated tool that evaluates job-related qualifications under human oversight.
• Final hiring decisions are made by trained personnel with meaningful human review.