Software Engineer – AI Inference Systems
Acceler8 TalentRole Overview
Acceler8 Talent is hiring a mid-level Software Engineer – AI Inference Systems. This is a full-time role in San Francisco, California. posted 5 days ago. Full responsibilities, required qualifications, and the apply link are listed in the description below.
Resume Keywords to Include
Make sure these keywords appear in your resume to improve ATS scoring
Job description
Software Engineer – AI Inference Systems
Series A AI Infrastructure Startup | Equity
AI inference is one of the biggest bottlenecks in modern infrastructure. This Series A startup is building the systems that maximise performance, efficiency and scale for next-generation AI workloads.
What You'll Do
- Build and optimise high-performance AI inference systems
- Improve scheduling, batching and concurrency
- Optimise KV cache management and memory efficiency
- Enable new model architectures in production
- Collaborate with compiler, kernel and distributed systems engineers to push performance to the limit
What You'll Bring
- Strong software engineering fundamentals
- Experience with ML inference or model serving
- Expertise in distributed systems and performance optimisation
- Python and/or C++
- Experience with TensorRT-LLM, vLLM or similar is a bonus
Why Join?
Join early, tackle some of the hardest engineering challenges in AI, and help build the infrastructure powering the next generation of intelligent applications.
Interested? Get in touch for a confidential conversation.
About Acceler8 Talent
Acceler8 Talent
Frequently Asked Questions
How do I apply for the Software Engineer – AI Inference Systems position at Acceler8 Talent?
Use the Apply button above to submit your application directly to Acceler8 Talent. Most applications take less than 5 minutes if your resume and contact details are ready, and you'll be routed to the employer's official application system to finish.
Where is the Software Engineer – AI Inference Systems position at Acceler8 Talent located?
This position is based in San Francisco, California. Acceler8 Talent has not indicated remote or hybrid options for this role, so candidates should plan for on-site work.
What does a Software Engineer – AI Inference Systems at Acceler8 Talent earn?
Acceler8 Talent has not disclosed a salary range in this posting. Many employers share specifics later in the interview process; you can also ask during a recruiter screen if compensation transparency is important to you.
When was the Software Engineer – AI Inference Systems role at Acceler8 Talent posted?
This role was posted on July 3, 2026 (5 days ago). It's still listed as actively hiring; we re-confirm openings against the source system multiple times per day and remove closed roles.
AI-powered job search
Get every job scored to your resume
Upload your resume and get jobs ranked, your resume tailored, and employee contacts found automatically.
Get started freeNo credit card to start