Lab Automation - Vision AI Engineer Intern

Xaira is an innovative biotech startup focused on leveraging AI to transform drug discovery and development. The company is leading the development of generative AI models to design protein and antibody therapeutics, enabling the creation of medicines against historically hard-to-drug molecular targets. It is also developing foundation models for biology and disease to enable better target elucidation and patient stratification. Collectively, these technologies aim to continually enable the identification of novel therapies and to improve success in drug development. Xaira is headquartered in the San Francisco Bay Area, Seattle, and London.

We are building a next-generation Vision AI platform that enables autonomous laboratory systems to understand, reason about, and interact with complex scientific environments.

Our goal is to develop generalized perception and spatial reasoning systems that minimize object-specific model training while enabling robots to interact with previously unseen laboratory equipment and consumables. Rather than training a new model for every instrument, we are building an AI reasoning layer that combines computer vision, multimodal AI, and intelligent workflow orchestration to create scalable laboratory autonomy.

As a Vision AI Engineer Intern, you will help design, benchmark, and deploy modern vision and multimodal AI systems while contributing to the architecture that connects perception, reasoning, and autonomous task execution. You will work closely with experienced AI and automation engineers and receive hands-on mentorship while contributing to production systems used in cutting-edge biotechnology research.

• →Design and develop an AI-driven state-machine architecture that orchestrates perception, reasoning, planning, and downstream task execution for autonomous laboratory workflows.
• →Benchmark computer vision, vision-language, and multimodal AI models for accuracy, robustness, inference latency, and deployment cost.
• →Design and evaluate AI architectures that combine computer vision, LLMs, and downstream task execution.
• →Develop generalized scene understanding and spatial reasoning pipelines that minimize object-specific model training.
• →Evaluate approaches for generalized object detection, object relationships, affordance recognition, and intention inference in laboratory environments.
• →Build scalable inference pipelines optimized for edge GPUs and cloud deployment.
• →Develop synthetic and augmented datasets using simulation platforms to improve model robustness and generalization.
• →Design benchmarking frameworks for evaluating perception models across diverse laboratory scenarios.
• →Collaborate with automation and robotics engineers to integrate perception systems into autonomous laboratory workflows.
• →Document model performance, deployment strategies, and architectural recommendations.
  
  

• Currently pursuing or recently completed a Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Machine Learning, Computer Vision, Robotics, or a related field.
• Strong software engineering skills in one or more modern programming languages (e.g., Python, C++, C#), with experience developing AI applications, cloud-based workflows, and production software systems.
• Experience with deep learning frameworks such as PyTorch or TensorFlow.
• Experience developing computer vision or multimodal AI projects through coursework, research, internships, or personal projects.
• Familiarity with object detection, segmentation, tracking, vision-language models, or scene understanding.
• Experience evaluating, training, or fine-tuning AI models.
• Strong curiosity for embodied AI, spatial reasoning, and real-world AI deployment.
  
  

• Experience with simulation platforms for synthetic or augmented data generation (Isaac Sim, Blender, MuJoCo, Unity, Habitat, etc.).
• Experience with foundation models, multimodal AI, LLMs, or agentic AI frameworks.
• Experience with agentic AI frameworks (LangGraph, OpenAI Agents SDK, AutoGen, PydanticAI), Model Context Protocol (MCP), or AI systems that integrate language models with external tools and software.
• Familiarity with ROS2, MoveIt, SLAM, Foxglove, or robotics software stacks.
• Experience deploying AI models on GPU edge devices (TensorRT, CUDA, ONNX).
• Experience with laboratory automation or scientific instrumentation.