Inference Engineering Lead

Inference Engineering Lead

Location: Remote, North America
Compensation: $290,000–$340,000 base salary

About the Opportunity

Fuel Talent is partnering with a growing AI technology company seeking an experienced Inference Engineering Lead to own the technical direction, architecture, and performance of its AI inference infrastructure.

This is a highly technical leadership opportunity for someone who thrives at the intersection of large language models (LLMs), distributed systems, and high-performance infrastructure.

The ideal candidate is a deeply hands-on engineer who enjoys solving complex technical challenges while providing direction, mentorship, and leadership to a growing engineering team.

This is not a traditional engineering management role. Approximately 80% of the position is hands-on technical work, with 20% focused on leadership and team development.

What You'll Do

• Own the technical strategy, architecture, and execution of large-scale LLM inference infrastructure.

• Lead efforts to optimize inference performance, throughput, latency, scalability, and reliability.

• Drive technical decisions around inference frameworks, model serving, GPU utilization, and infrastructure efficiency.

• Work hands-on with inference systems, troubleshooting complex issues and implementing production-ready solutions.

• Evaluate and implement technologies that improve model serving performance and operational efficiency.

• Partner with infrastructure and engineering teams to support the expansion of compute capacity and production environments.

• Establish technical standards, engineering best practices, and long-term architectural direction.

• Mentor and guide engineers, providing technical leadership while remaining deeply involved in implementation.

• Help build and develop a small, high-performing engineering team.

• Collaborate with cross-functional stakeholders to align technical priorities with product and business objectives.

• Balance performance, reliability, and infrastructure costs as the platform scales.

What We're Looking For

• Extensive software engineering experience with deep expertise in LLM inference, model serving, and AI infrastructure.

• Strong understanding of inference optimization, including latency, throughput, batching, caching, and GPU utilization.

• Experience with modern LLM inference frameworks, particularly vLLM or comparable technologies.

• Strong background in distributed systems, scalable infrastructure, and production engineering.

• Experience designing, deploying, and optimizing high-performance inference systems in production environments.

• Demonstrated technical leadership experience, including setting engineering direction, mentoring developers, and driving complex initiatives.

• Ability to lead and motivate a team while remaining an active individual contributor.

• Strong interpersonal skills, emotional intelligence, and a collaborative leadership style.

• Excellent communication skills with the ability to influence technical decisions and build alignment across teams.

• Comfort operating in a fast-moving environment with significant autonomy and ownership.

Nice to Have

• Experience with GPU infrastructure, distributed inference, or large-scale AI workloads.

• Familiarity with inference optimization techniques such as quantization, continuous batching, and KV-cache management.

• Experience working with Kubernetes, container orchestration, or high-performance computing environments.

• Exposure to infrastructure capacity planning or large-scale compute deployments.

• Experience helping build or scale an engineering team in a startup or high-growth technology company.

What Makes This Opportunity Exciting

• Technical ownership: Set the direction for a critical engineering function and have meaningful influence over architectural decisions.

• Hands-on leadership: Stay close to the code and technical challenges while mentoring and developing other engineers.

• Infrastructure growth: Help shape and scale the infrastructure supporting next-generation AI products.

• Team building: Play a key role in developing a specialized, high-performing engineering team.

• Competitive compensation: $290,000–$340,000 base salary.

• High-impact environment: Join a growing organization where technical decisions directly influence product performance and business growth.

Who Will Thrive Here

We're looking for someone who combines exceptional technical depth with genuine leadership ability.

You may currently be a Staff Engineer, Principal Engineer, Tech Lead, or Engineering Lead working on LLM inference or AI infrastructure.

You're someone who can architect complex systems, dive into the code to solve difficult problems, and bring engineers together around a clear technical vision.

Most importantly, you're a collaborative, approachable leader who earns trust through technical credibility, strong communication, and a willingness to remain hands-on.