Senior ML Systems Engineer — SmartRouter & Inference Cost (Remote)

Deliverance AI; United States; Remote; USD 119,000 - 172,000; Full time

Benefits offered by this job

Equity participation

Competitive cash compensation

Job summary

Deliverance AI seeks a senior engineer to build routing and cost-management systems that decide which model handles each request. The role sits at the intersection of backend engineering, ML systems, inference economics, and evaluation, with a focus on reliability and cost efficiency.

Based in London or remote, the position offers remote-friendly arrangements across the UK, EU, and selected global time zones, plus equity participation and competitive cash compensation.

Qualifications

• Experience in backend engineering, ML systems, or platform engineering with a strong focus on cost and performance.
• Practical knowledge of model serving, inference workflows, evaluation, and multi-provider integrations.
• Demonstrated ability to use data to optimise complex systems and make measurable trade-offs.
• Familiarity with telemetry, cost attribution, dashboards, or FinOps practices for compute-intensive services.
• Comfort owning a system whose success is assessed directly through reliability, quality, and customer savings.
• Clear thinking about explainability, controls, and auditability in automated routing decisions.

Responsibilities

• Implement request classification and routing across smaller, mid-tier, and frontier model options.
• Integrate multiple model providers and account for differences in capabilities, latency, pricing, and operational behavior.
• Measure inference cost end to end and expose current usage and savings through real-time FinOps dashboards.
• Optimise the cost-versus-quality frontier using evaluation datasets, guardrails, and production performance data.
• Design routing decisions and supporting telemetry so outcomes can be explained, reviewed, and audited.
• Own improvements against customer-facing efficiency measures, including demonstrable reductions in model spend where quality remains acceptable.

Skills

Backend engineering

ML systems

Platform engineering

Data-driven optimization

Telemetry/FinOps

Tools

Model serving

Inference workflows

Multi-provider integrations

Job description

Deliverance AI seeks a senior engineer to build routing and cost-management systems that decide which model handles each request. The role sits at the intersection of backend engineering, ML systems, inference economics, and evaluation, with a focus on reliability and cost efficiency.

Based in London or remote, the position offers remote-friendly arrangements across the UK, EU, and selected global time zones, plus equity participation and competitive cash compensation.