Software Engineer, AI Infrastructure - LVM Inference & Evaluation
Ambient.ai2 months ago
Redwood City, CA, USAMid Level
H1B sponsor
Base Salary
$168k - $205k/yr
Responsibilities
- Design, build, and maintain infrastructure for real-time computer vision, LLM, LVM, and multimodal inference workloads.
- Build scalable systems for processing large volumes of video and sensor data.
- Optimize inference latency, throughput, GPU utilization, reliability, and cost.
- Develop evaluation harnesses, benchmarks, regression tests, and continuous model-evaluation systems.
- Build model-serving architecture using techniques such as batching, caching, quantization, model parallelism, and hardware optimization.
- Partner with research scientists and product engineering teams to productionize advances in computer vision, LLMs, LVMs, RAG, and multimodal AI.
- Develop data engines and feedback loops for training-data collection, model evaluation, and continuous AI improvement.
- Create observability, monitoring, and debugging tools for production AI systems.
- Help establish practices for deploying and operating AI systems in enterprise environments.
Requirements
- At least 2 years of industry experience building infrastructure, distributed systems, machine-learning platforms, or production AI systems.
- BS or MS in Computer Science or a related technical field, or equivalent practical experience.
- Strong programming ability, particularly in Python, with solid software-engineering fundamentals.
- Experience building scalable machine-learning infrastructure for training, inference, evaluation, and deployment.
- Hands-on experience running deep-learning models in production, ideally including LLMs, LVMs, vision-language models, or multimodal models.
- Strong understanding of inference optimization, including batching, caching, quantization, parallelism, memory optimization, GPU utilization, and latency reduction.
- Experience with model-serving frameworks such as vLLM or Triton Inference Server.
- Experience building evaluation frameworks, test harnesses, benchmarks, regression tests, or model-quality measurement systems.
- Strong machine-learning and deep-learning background; computer vision experience is a plus.
- Experience designing data engines or pipelines for training and evaluation data.
- Familiarity with LLMs, LVMs, RAG pipelines, embedding models, or multimodal models in production applications.
- Experience with cloud infrastructure, containers, orchestration, distributed systems, and GPU workloads.
- Strong collaboration and communication skills, ownership, problem-solving ability, and adaptability.
- Preferred experience includes large-scale GPU infrastructure, CUDA, NCCL, PyTorch, TensorRT, ONNX, video understanding, model compression, speculative decoding, distillation, pruning, prompt evaluation, human-in-the-loop evaluation, vector databases, search infrastructure, or internal ML platforms.
Benefits
- Regular full-time employees receive stock options.
- Comprehensive medical, dental, vision, life, EAP, legal services, and 401(k) benefits.
- Flexible time off, including a winter break for most roles depending on customer demand.
- Latest technology and company swag delivered to employees.
- Hybrid work arrangement: Redwood City engineering teams work in the office three days per week, while other Bay Area employees come in on Fridays.
- Opportunities for employee connection and team activities.
Categories
About Ambient.ai
Ambient.ai builds enterprise physical security software that uses computer vision and AI to detect threats and automate response across video, access control, and sensor data. The SaaS platform integrates with existing cameras and PACS to unify monitoring, investigations, and incident orchestration for large facilities. Founded in 2016 and headquartered in Redwood City, California, the privately held company serves enterprises across campuses, data centers, and critical infrastructure.