Software Engineering Director - Inference Platform
About the team
The SambaStack team builds the inference serving platform enterprises and service providers use to host foundation models on RDU hardware. The platform is cloud-agnostic, and the team owns deployment, orchestration, scaling, and reliability for production inference workloads.
About the Role
The SambaStack team is seeking an Engineering Director to lead a software engineering team while remaining a hands-on technical contributor. You'll own the growth and effectiveness of your team, the technical quality of their output, and the roadmap for the inference serving platform. You'll continue to design systems and write code on the platform's hardest problems.
Responsibilities
People & Team Leadership
Lead, grow, and inspire a software team, fostering a culture of technical excellence, collaboration, and continuous improvement
Own hiring for your team: define roles, assess candidates, and build a diverse, high-performing engineering organization
Drive the career development of your engineers through regular 1:1s, meaningful feedback, and clear growth plans
Set clear goals and expectations, track team progress, and remove blockers to keep the team executing effectively
Partner with Product, ML, QA, and DevOps leadership to align team priorities with broader organizational objectives
Technical Contribution
Contribute directly as a software engineer: designing systems, writing code, and leading implementation on critical platform initiatives
Participate in and lead design reviews, providing authoritative technical guidance on major features and cross-cutting changes
Establish and uphold engineering standards, best practices, and coding quality across the team
Proactively identify and drive the resolution of systemic risks: performance bottlenecks, reliability gaps, and scaling constraints
Stay current on emerging technologies and AI inference trends to inform the team's technical direction
Required Qualifications
12+ years of software engineering experience, including 2+ years leading and managing engineering teams
Demonstrated ability to manage, develop, and hire strong engineers while remaining a hands-on technical contributor
Strong technical depth in backend systems built with Python, Go, or Rust
Experience with AI inference serving, orchestration, and the infrastructure challenges of LLM workloads at production scale
Proven ability to drive engineering excellence across an engineering team
Excellent communication skills: able to work effectively with engineers, cross-functional partners, and senior leadership
Experience running iterative engineering processes in a fast-paced environment
Preferred Qualifications
Experience with Kubernetes ecosystem tooling, including Operators and Helm Charts
Background in ML application optimization and productionization
Experience building or managing teams that deliver cloud-native platforms for enterprise customers
Familiarity with AI coding assistants and the developer tooling ecosystem
Experience at a high-growth AI infrastructure company
Base Salary Range:
Base Pay Range
$245,000—$325,000 USD