Founder VP AI Inference (SW)

Blue Signal Search; United States; Hybrid; USD 350,000 - 550,000; Full time

Job summary

Blue Signal Search is seeking a senior software leader for a founder-level role shaping the next era of high-performance AI inference. You will architect and guide the software stack, drive hardware acceleration strategy, and recruit top engineering talent.

You will influence product direction, lead a small elite team, and partner with founders to define the roadmap while delivering production-ready systems at scale.

Qualifications

• Deep experience building or optimizing production scale AI inference or distributed systems software for accelerator rich environments.
• Strong systems background in GPU programming, kernel optimization, runtime design, communication layers, caching, batching, or scheduling.
• Track record of shipping technically difficult platforms where performance, reliability, and scalability all matter.
• Experience leading senior engineers and attracting top talent, with the judgment to balance urgency and long-term architecture.
• Familiarity with modern model serving patterns, speculative execution approaches, and performance measurement for large scale AI workloads.
• Comfortable operating in an early-stage company where ambiguity is high and leaders help define the playbook.

Responsibilities

• Lead architecture and delivery of a high-performance AI inference software stack spanning runtime, scheduling, serving, and system optimization.
• Build and mentor a small elite engineering team while remaining hands on with code, technical design, and execution.
• Partner with founders to shape product roadmap, infrastructure strategy, and the path from software acceleration into programmable hardware and future silicon.
• Improve throughput, latency, utilization, and cost efficiency across modern accelerator-based deployments and distributed environments.
• Work closely with strategic customers and ecosystem partners to support real world production adoption and performance tuning.
• Establish engineering standards for hiring, release quality, experimentation, and cross functional collaboration in a fast-moving startup setting.

Skills

AI inference

Distributed systems

GPU programming

Kernel optimization

Runtime design

Scheduling

Leadership

Job description

A confidential, venture-backed AI systems company is hiring a senior software leader to help shape the next era of high-performance inference. This is a rare opportunity to step into a founder-level seat where you can influence architecture, team design, product direction, and the long-term path from software acceleration into programmable hardware and future silicon. The ideal candidate brings deep technical judgment, strong leadership presence, and the ability to build credibility with elite engineers, founders, and external partners alike.

What You Will Do

• Lead architecture and delivery of a high-performance AI inference software stack spanning runtime, scheduling, serving, and system optimization.
• Build and mentor a small elite engineering team while remaining hands on with code, technical design, and execution.
• Partner with founders to shape product roadmap, infrastructure strategy, and the path from software acceleration into programmable hardware and future silicon.
• Improve throughput, latency, utilization, and cost efficiency across modern accelerator-based deployments and distributed environments.
• Work closely with strategic customers and ecosystem partners to support real world production adoption and performance tuning.
• Establish engineering standards for hiring, release quality, experimentation, and cross functional collaboration in a fast-moving startup setting.

What We Are Looking For

• Deep experience building or optimizing production scale AI inference or distributed systems software for accelerator rich environments.
• Strong systems background in one or more of GPU programming, kernel optimization, runtime design, communication layers, caching, batching, or scheduling.
• Track record of shipping technically difficult platforms where performance, reliability, and scalability all matter.
• Experience leading senior engineers and attracting top talent, with the judgment to balance urgency and long-term architecture.
• Familiarity with modern model serving patterns, speculative execution approaches, and performance measurement for large scale AI workloads.
• Comfortable operating in an early-stage company where ambiguity is high and leaders help define the playbook.

What Makes This Opportunity Stand Out

• Founder-level influence on both technical strategy and team formation.
• Meaningful exposure to cutting edge AI infrastructure work with real production impact.
• High autonomy, direct access to leadership, and room to shape the function without heavy micromanagement.
• Competitive executive compensation and meaningful equity participation.
• Opportunity to help define how advanced inference software evolves alongside next generation hardware initiatives.