SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 200,000 - 400,000 / annual
Inferact, founded by the creators and core maintainers of vLLM, is building the world's AI inference engine. The company sits at the intersection of models and hardware, working to make inference cheaper and faster.
You will lead a team of exceptional senior engineers across inference systems, performance, kernels, accelerators, and cloud infrastructure. This is a deeply technical management role where you own team execution, hiring, coaching, prioritization, and operating rhythm while staying close enough to the work to earn the trust of engineers solving hard systems problems.
Key responsibilities include:
- Building and scaling a world-class, senior-heavy engineering organization
- Leading team execution, hiring, and coaching while maintaining technical quality and execution speed
- Partnering with engineering and company leadership to translate company priorities into clear technical direction
- Removing blockers and improving how the team works
- Helping every engineer do the highest-leverage work of their career
- Owning the full people-management lifecycle: hiring, onboarding, 1:1s, feedback, performance management, career development, team health, and retention
- Building effective engineering operating rhythms around planning, decision-making, technical reviews, cross-team coordination, and accountability
- Demonstrating strong judgment about when to dive into technical problems, when to delegate, and how to create leverage for senior engineers
Requirements:
- Bachelor's degree or equivalent experience in computer science, engineering, or similar
- Demonstrated experience managing strong software engineers in technically demanding systems, infrastructure, ML systems, distributed systems, or performance-oriented environments
- Strong technical credibility with the ability to understand architecture, ask useful questions, challenge assumptions, and help unblock senior engineers without becoming a bottleneck
- Experience owning the full people-management lifecycle, including hiring, onboarding, 1:1s, feedback, performance management, career development, team health, and retention
- Ability to translate ambiguous company priorities into clear team goals, sequencing, ownership, and execution plans while maintaining urgency in a fast-changing startup environment
- Track record of building effective engineering operating rhythms around planning, decision-making, technical reviews, cross-team coordination, and accountability without creating unnecessary process
- Strong judgment about when to dive into a technical problem, when to delegate, and how to create leverage for senior engineers rather than competing with them for ownership
- 2+ years of management experience with 10+ reports
Preferred qualifications:
- Experience leading teams working on AI/ML infrastructure, model serving, distributed systems, GPU infrastructure, compilers, performance engineering, cloud infrastructure, or developer platforms
- Experience managing senior, staff, principal, research-adjacent, or PhD engineers in an environment where technical credibility and autonomy are especially important
- Experience scaling an engineering team through rapid hiring, including interviewer calibration, hiring decisions, onboarding systems, and thoughtful team design
- Familiarity with inference systems and adjacent technologies such as vLLM, SGLang, PyTorch, CUDA/Triton, Kubernetes, distributed serving, or accelerator infrastructure
- Experience partnering closely with founders or engineering executives in an early-stage company where priorities, team boundaries, and organizational needs evolve quickly
- Built or scaled a small, unusually high-talent engineering team where the technical surface area was specialized and the quality bar was extremely high
- Previously remained hands-on as an engineer or technical lead before moving into management and can still reason credibly about complex production systems
- Managed teams spanning multiple technical specialties, geographies, or time zones while preserving strong ownership and communication
- Helped establish engineering management practices from an early stage rather than inheriting a mature management system
- Contributed to open-source infrastructure, AI systems, developer tools, or technically ambitious products used by external engineers
