AI Engineer

About The Company
Bright.AI is a high-growth Physical AI company dedicated to transforming how businesses interact with the physical world through intelligent automation. Our cutting-edge AI platform processes visual, spatial, and temporal data from billions of real-world events captured across edge devices, mobile sensors, and cloud infrastructure. This enables us to facilitate intelligent decision-making at scale, revolutionizing industries by providing real-time insights and automation solutions. Our commitment to innovation and excellence positions us as a leader in the Physical AI space, continuously pushing the boundaries of what is possible with artificial intelligence and machine learning technologies.
About The Role
We are seeking a highly skilled and innovative Senior AI Engineer specializing in Large Language Models (LLMs) and Retrieval Augmented Generation (RAG) systems. In this pivotal role, you will lead the development of advanced AI systems that integrate LLMs with real-world knowledge sources to create intelligent assistants. These assistants will support technicians and operators in troubleshooting complex issues within industrial environments, such as manufacturing plants, energy facilities, and logistics hubs. Your work will sit at the intersection of natural language processing, foundational models, and real-time information systems, contributing to the creation of conversational tools that turn manuals, technician notes, and sensor data into actionable guidance. This role offers a unique opportunity to influence the future of industrial automation and AI-driven decision support systems.
Qualifications
The ideal candidate will possess a strong educational background in Computer Science, AI, Machine Learning, or related fields, with specialization in NLP or deep learning. A Master’s or Ph.D. in these areas is preferred. Candidates should demonstrate a robust research or applied experience with large language models and retrieval augmented generation systems. Prior experience with agentic RAG systems is highly desirable. The candidate must have a minimum of five years of experience in machine learning or AI, with a focus on NLP, LLMs, or conversational AI. Fluency with modern LLMs and open-source foundational models such as LLAMA, Falcon, Mistral, GPT, or Claude is essential. Expertise in building RAG pipelines using tools like LangChain, LlamaIndex, or custom vector databases, along with experience in prompt engineering, instruction tuning, and fine-tuning models, is required. A deep understanding of document retrieval techniques, semantic search, embedding generation, similarity metrics, and vector stores such as FAISS, Weaviate, or Pinecone is necessary. Strong proficiency in Python and familiarity with ML frameworks like PyTorch or Hugging Face Transformers are also critical. Additionally, experience with integrating AI into real-world applications with user-facing interfaces and operational constraints is highly valued.
Responsibilities

• Lead the architecture and development of RAG systems that combine large language models with structured and unstructured external information sources to enhance industrial troubleshooting capabilities.
• Design and develop AI-powered assistants that support technicians in diagnosing and resolving anomalies or failures within factory, plant, or industrial settings.
• Build robust pipelines for ingesting, preprocessing, and indexing large collections of documents, including manuals, logs, notes, and procedures, to enable semantic search and grounding.
• Customize and fine-tune foundational models to incorporate domain-specific language, tone, and logic tailored for industrial troubleshooting scenarios.
• Collaborate closely with product, data, and cloud teams to design scalable, privacy-compliant, and latency-sensitive LLM applications suitable for industrial environments.
• Develop evaluation strategies to measure system performance, accuracy, and user experience, ensuring continuous improvement in RAG-enabled solutions.
• Stay informed about the latest advancements in LLM architectures, retrieval methods, prompt engineering, and emerging AI techniques, integrating these into the product development roadmap.

Benefits
At Bright.AI, we are committed to providing an enriching work environment that fosters innovation and professional growth. Our employees enjoy competitive compensation packages, comprehensive health benefits, and opportunities for continuous learning and development. We promote a collaborative culture that encourages knowledge sharing and cross-disciplinary teamwork. Employees also benefit from flexible work arrangements, cutting-edge tools and resources, and the chance to work on impactful projects that are shaping the future of industrial AI. Joining Bright.AI means becoming part of a dynamic team dedicated to pushing technological boundaries and making a tangible difference in the world.
Equal Opportunity
Bright.AI is an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees. We do not discriminate based on race, religion, color, national origin, gender, sexual orientation, age, disability, or any other protected status. We believe that a diverse team fosters innovation and drives success, and we are dedicated to providing equal employment opportunities to all qualified candidates.