About the Company – Sword Health

Sword Health is a digital health startup founded by a mix of engineers and medical doctors, transforming healthcare through AI-driven solutions.

• Mission: Deliver world-class healthcare anytime, anywhere via the AI Care platform, reducing costs for payers, employers, and health systems.

• Specialties: AI-powered rehabilitation, women’s health, movement health, pain care, and mental health.

• Impact: Since 2020, over 700,000 members across three continents have completed 10 million AI sessions, helping 1,000+ enterprise clients avoid over $1 billion in unnecessary healthcare costs.

• Innovation: Backed by 42 clinical studies and 44+ patents, and raised $500M+ from investors like Khosla Ventures, General Catalyst, and Founders Fund.

Sword Health’s culture is mission-driven, innovative, and collaborative, seeking top talent to push boundaries in AI and healthcare technology.

About the Role

Salary: £66,500 – £104,500 per year (includes base, variable, and equity)
Job Type: Full-time

As a Senior AI Infrastructure Engineer, you will own the infrastructure powering Sword Health’s AI Care platform. This includes deploying AI models for movement analysis, conversational AI, and real-time voice agents at scale and low latency, ensuring millions of sessions run efficiently worldwide.

This role sits at the intersection of ML and infrastructure, focusing on AI-specific challenges like GPU orchestration, LLM inference optimization, computer vision, and real-time AI agent systems.

Key Responsibilities

• Design, build, and maintain inference infrastructure for AI models

• Deploy and manage real-time computer vision, large language models, and AI voice agents

• Architect and scale Kubernetes clusters for GPU workloads

• Build low-latency AI agent infrastructure including WebRTC, STT, and TTS systems

• Optimize AI inference with techniques like speculative decoding, batching, and model parallelism

• Develop and maintain Infrastructure as Code (Terraform) and GitOps workflows

• Monitor GPU utilization, model latency, throughput, and reliability

• Collaborate with ML engineers, data scientists, and product teams

• Mentor team members in AI infrastructure best practices

Required Experience & Skills

• 5+ years in infrastructure engineering, including 2+ years on AI/ML workloads in production

• Strong experience with Kubernetes for GPU workloads

• Hands-on experience with model serving & inference optimization for CV and LLM workloads

• Understanding of LLM inference techniques, speculative decoding, batching, quantization

• Real-time AI infrastructure experience: WebRTC, voice agents, STT/TTS

• Infrastructure as Code expertise (Terraform/GitOps)

• Linux systems fundamentals and networking knowledge for low-latency real-time workloads

• Fluent English and a proactive, ownership-driven mindset

Preferred / Nice-to-Have

• Experience with NVIDIA Triton, TensorRT, vLLM, NVIDIA Riva

• Experience with Istio, Kafka, Prometheus, ELK, Vault, Redis, MySQL

• Cloud infrastructure experience (AWS, Azure, GCP)

• Python, Go, or similar programming languages

• Familiarity with SCRUM methodology

Benefits

US Employees:

• Health, dental, vision insurance

• Equity shares

• Flexible hours, remote-first, unlimited vacation

• 401(k) plan, parental leave, paid company holidays

• Digital therapist access

Portugal Employees:

• Health, dental, vision insurance

• Meal & remote work allowance

• Flexible hours, work-from-home options

• Equity shares, discretionary vacation

• English classes, snacks, and beverages

Other:

• Career growth opportunities

• Work in a fast-paced, mission-driven environment

Work Eligibility

• US applicants must have the legal right to work in the US (no sponsorship provided)

• Portugal applicants must have a valid EU visa and reside in Portugal

• No relocation assistance is offered

Equal Opportunity

Sword Health is an equal opportunity employer and does not discriminate based on age, gender, race, religion, disability, sexual orientation, or veteran status.