Senior AI Engineer – RAG Systems

Bright.AI is a high-growth Physical AI company transforming how businesses interact with the physical world through intelligent automation. Our AI platform processes visual, spatial, and temporal data from billions of real-world events—captured across edge devices, mobile sensors, and cloud infrastructure—to enable intelligent decision-making at scale.

We are now hiring a Senior AI Engineer – LLM, RAG to lead the development of Retrieval-Augmented Generation (RAG) systems that harness the power of large language models (LLMs) and real-world knowledge sources. This role is pivotal to building next-generation intelligent assistants that help technicians and operators troubleshoot complex issues in industrial settings.

You’ll work at the intersection of NLP, foundational models, and real-time information systems—developing intelligent tools that turn manuals, technician notes, and sensor data into actionable, conversational guidance for the physical world.

Responsibilities

• Lead the architecture and development of RAG systems that combine LLMs (e.g., LLAMA, Mistral, Claude, GPT) with structured and unstructured external information sources.
• Develop AI-powered assistants to support technicians in diagnosing and resolving anomalies or failures in factory, plant, or industrial settings.
• Build pipelines to ingest, preprocess, and index large corpora of documents (manuals, logs, notes, procedures) for semantic search and grounding.
• Customize and fine-tune foundational models to incorporate domain-specific language, tone, and logic for industrial troubleshooting scenarios.
• Collaborate with product, data, and cloud teams to design scalable, privacy-compliant, and latency-sensitive LLM applications.
• Design evaluation strategies to measure performance, accuracy, and user experience of RAG-enabled systems in production settings.
• Stay up to date with the latest advances in LLM architectures, retrieval methods, and prompt engineering, and integrate emerging techniques into the product roadmap.

Educational Background

• M.S. or Ph.D. in Computer Science, AI, Machine Learning, or a related field, with specialization in NLP or deep learning.
• Strong research or applied background in large language models (LLMs) and retrieval-augmented generation (RAG) systems. Agentic RAG experience is highly desirable.

Required Skills & Expertise

• 5 years of experience in machine learning or AI with a strong focus on NLP, LLMs, or conversational AI.
• Fluency with modern LLMs and open-source foundational models (e.g., LLAMA, Falcon, Mistral, GPT, Claude).
• Experience building RAG pipelines with tools like LangChain, LlamaIndex, or custom vector database integrations, with at least one production grade system was built.
• Fluency with prompt engineering, instruction tuning, or fine-tuning open-source models.
• Deep understanding of document retrieval (semantic search, embedding generation, similarity metrics) and vector stores (e.g., FAISS, Weaviate, Pinecone).
• Strong foundation in core machine learning techniques, including experience with reinforcement learning (RL) or decision-making models.
• Proficiency with ML development frameworks such as PyTorch, Hugging Face Transformers, or similar.  Strong Python programming is a must.
• Experience integrating AI systems into real-world applications with user-facing interfaces and operational constraints.
• Excellent problem-solving and critical thinking skills; ability to design solutions for complex, ambiguous problems.
• Strong written and verbal communication skills, with ability to collaborate cross-functionally with engineers, product managers, and domain experts.

Bonus Qualifications

• Experience applying LLMs in industrial or physical infrastructure settings (e.g., manufacturing, logistics, utilities, energy).
• Knowledge of industrial control systems, maintenance workflows, or technician support processes.
• Exposure to multimodal models or integrating textual data with sensor and/or time-series data.
• Prior experience in a startup or a fast-paced environment building LLM-powered products from the ground up.