Software Engineer, AI Infrastructure | LUMIQO | Handshake

LUMIQO; United States; Remote; USD 96,000 - 179,000; Full time

Job summary

Lumiqo is a clinical AI startup seeking a Software Engineer focused on infrastructure to join our technical team and help scale our AI capabilities in oncology trials. You will work remotely with a strong emphasis on infrastructure and developer experience.

As part of the role, you will architect the stack, ship production code for LLM-based features, and operate inference and serving systems with cost-efficient compute. Remote work, with a May 2026 start window.

Qualifications

• Hands-on experience leading the design, deployment, or scaling of production AI infrastructure.
• 3+ years shipping production AI or infrastructure systems.
• Strong programming fundamentals.
• Production experience with RAG architectures and vector databases.
• Ability to navigate ambiguous problems and drive cross-functional resolution.

Responsibilities

• Architect and connect the underlying technology stack that powers our AI capabilities end-to-end.
• Ship production code that powers our LLM-based AI capabilities.
• Build and operate the inference and serving infrastructure for our AI system.
• Set up model deployment, autoscaling, and cost-efficient compute.
• Set technical direction for how Lumiqo operates AI infrastructure as we scale.

Skills

AI infrastructure

Platform engineering

Production deployment

LLM expertise

Cross-functional collaboration

Tools

Databricks

AWS Bedrock

GCP Vertex AI

Azure ML

Vector databases

Job description

About the job

4-6 weeks | Remote | Start: May 2026 | $70-130/hr

Lumiqo is a clinical AI startup building an AI-assisted adverse event detection tool for oncology clinical trials. With a patent-pending architecture in hand, we're looking for a Software Engineer with a passion for infrastructure and developer experience to join our technical team and help us build and scale our product.

What you'll do:

• Architect and connect the underlying technology stack that powers our AI capabilities end-to-end


• Ship production code that powers our LLM-based AI capabilities


• Build and operate the inference and serving infrastructure for our AI system


• Set up model deployment, autoscaling, and cost-efficient compute


• Set technical direction for how Lumiqo operates AI infrastructure as we scale

What we're looking for:

• Hands-on experience leading the design, deployment, or scaling of production AI infrastructure, particularly around model serving, deployment pipelines, or platform engineering


• 3+ years' experience with demonstrated success in shipping production AI or infrastructure systems


• Strong programming fundamentals


• Production experience with RAG architectures and vector databases


• Comfort with ambiguity and the ability to drive cross-functional problems to resolution

Bonus points for:

• Deploying or serving LLMs in production (any provider or framework)


• Familiarity with platforms such as Databricks, AWS Bedrock, GCP Vertex AI, Azure ML, or similar


• Medical NLP or clinical AI background


• HIPAA infrastructure