AI Research Engineer - Robotics

At Coram AI, we’re reimagining video security for the modern world. Our cloud-native platform uses computer vision and AI to help businesses stay safe, make smarter decisions, and move faster; from real-time alerts to seamless clip sharing and multi-site visibility. You’ll be joining an ambitious, fast-moving team that values clarity, craftsmanship, and impact. Every person here has a voice, ships meaningful work, and helps shape how AI can make the world safer and more connected. The role: As an AI Research Engineer, you will focus primarily on deploying high-performance vision and multimodal models onto robotic platforms where latency, reliability, and hardware constraints matter. Responsibilities: - Deploy deep learning models on edge devices and in the cloud for real-time inference - Fine-tune models on proprietary datasets and manage dataset versioning, labeling, and evaluation - Write high-quality C++ or Rust code for deterministic, low-latency execution - Build cloud pipelines that process millions of images and video streams in near real time - Perform model surgery in PyTorch and TensorRT, including pruning, quantization, and graph optimization - Optimize GPU utilization, memory footprint, and inference throughput - Build and maintain middleware for real-time IPC between perception, planning, and control systems - Profile production systems to diagnose memory, compute, and concurrency bottlenecks - Design rigorous evaluation loops to measure model accuracy, latency, and robustness in field conditions Skills and qualifications: - BS, MS, or PhD in Computer Science, Robotics, Electrical Engineering, or a related technical field - 3+ years of experience building robotics, perception, or real-time systems (startup or high-performance production environments strongly preferred) - Experience deploying neural networks under strict latency constraints where milliseconds matter - Deep understanding of GPU memory management, batching strategies, and compute optimization - Strong debugging skills using profilers and low-level performance tools - Solid experience with PyTorch; experience with TensorRT and ONNX is highly desirable - Deep expertise in C++ preferred; strong Rust or Python experience also welcome - Experience building production systems that must be reliable, observable, and fault-tolerant - Experience with vLLM, SGLang, or high-performance LLM inference engines is a plus - Experience deploying multimodal models or LLMs in robotics contexts is a plus - Experience with distributed systems, structured logging, and observability at scale is a plus - Familiarity with distributed pubsub, real-time Linux, or embedded GPU platforms is a plus - Experience working with NVIDIA Jetson, CUDA kernels, or custom accelerators is a plus - Resilient in challenging and fast-paced environments - Exceptional written and verbal communication skills in English, with the ability to influence at all levels - Ability to work in an onsite environment What we offer: - 100% Employer-paid medical, dental, vision, and base life insurance - Flexible paid time off and 10 paid holidays - 401(k) with both Traditional and Roth options - Early-stage equity in a rapidly growing company - Referral bonuses - Daily team breakfast and dinner, and regular team off-sites - Free onsite EV charging - The latest Apple products and unlimited tech stack (Claude Cowork, Perplexity Computer, Nooks, Clay, Instantly, etc.) - Direct exposure to our AI-native GTM machinery We're on a mission to transform a $50B+ legacy industry by bringing the power of cutting-edge multimodal LLMs and computer vision to real-world security and operations. From firearm detection to intelligent access control, our AI-native platform turns every camera and sensor into a smart system that enhances safety, efficiency, and awareness. Founded by Ashesh Jain (ex-Lyft Level 5, PhD Cornell) and Peter Ondruska (ex-Lyft, PhD Oxford), Coram AI is backed by Ansa Capital, Battery Ventures, Mosaic, 8VC