![]()
Title: Machine Learning Inference Engineer
Location: San Francisco, CA - Hybrid
Salary: $200K-$250K + Equity
A rapidly growing AI startup is hiring a Machine Learning Inference Engineer to help optimize and scale production machine learning systems. The company is building next-generation AI applications and is looking for an engineer who enjoys solving complex performance challenges across model serving and inference infrastructure. This is a startup environment where engineers take ownership over their work, collaborate closely with leadership, and have a direct impact on the performance and scalability of production AI systems.
This role is focused on productionizing machine learning models and optimizing inference performance at scale. You will build high-performance model-serving infrastructure, improve latency, throughput, and compute efficiency, and work across GPU optimization, distributed inference, and production deployment. This is a hands-on engineering role ideal for someone passionate about building scalable AI infrastructure and making machine learning systems faster, more efficient, and production-ready.
Experience:
* 2+ years of experience in Machine Learning Engineering or AI Infrastructure
* Strong Python and PyTorch experience building production ML systems
* Experience with inference frameworks such as Triton, TensorRT, vLLM, or similar
* Experience optimizing model latency, throughput, and infrastructure cost
* Experience with model optimization techniques such as pruning, distillation, or KV caching
* Understanding of GPU infrastructure and deploying ML models at scale
* Experience with diffusion models, multimodal AI, or large-scale vision systems is a plus
Benefits:
* Equity
* Paid Time Off
* Medical, dental, and vision coverage
* Opportunity to create lasting impact within a growing organization
* Hybrid working schedule
Oscar Associates Limited (US) is acting as an Employment Agency in relation to this vacancy.
Never miss an opportunity! Create an alert based on the job you applied for.