Confidential · 1 day ago
Senior Software Developer - AI Architect (LLM/RAG)
Confidential is a leading provider of clean nuclear power generation technology, seeking a Senior Software Developer - AI Architect. This role involves leading the architecture, design, and implementation of core LLM/RAG systems to deliver a scalable, production-ready platform while collaborating with various teams and mentoring junior developers.
Marketing & Advertising
Responsibilities
Architect and build coherent, useful LLM pipelines, including agentic systems and knowledge base integrations
Design and implement knowledge management systems (i.e. RAG, CAG) for enhanced AI capabilities
Oversee and contribute to the fine-tuning of LLMs for specific educational and research applications
Ensure system architecture is designed for scalability, observability (logging and evaluation), and efficiency
Integrate third-party AI systems and services following organizational integration strategies
Collaborate closely with full-stack and build engineers to ensure a cohesive and functional product
Provide expert input on technology choices, potentially overriding initial platform decisions based on deep industry knowledge
Mentor junior developers and student assistants in AI implementation best practices
Communicate complex AI concepts to non-technical stakeholders across the organization
Support student projects and competitions by providing AI technical expertise
Work with faculty, program directors, and other departments to implement AI-powered solutions
Assist with setting up AI resources for students participating in xFoundry programs
Qualification
Required
Master's or Ph.D. in Computer Science, Machine Learning, Artificial Intelligence, or related field preferred; Bachelor's degree with exceptional experience considered
8+ years of professional experience in machine learning/AI, with extensive foundational experience in machine learning valued more highly than brief, recent-only LLM experience
Deep knowledge of Python and advanced programming concepts
Experience with LLM pipeline construction (e.g., LangChain, LlamaIndex, Haystack)
Proven experience with LLM fine-tuning and model optimization
Expertise with ML frameworks like TensorFlow, PyTorch, or JAX
Experience with broader AI concepts including CNNs, transformers, and data classification
Proficiency with vector databases (Pinecone, Weaviate, Chroma, FAISS)
Experience with cloud platforms (AWS, Azure, Google Cloud) for ML workloads
Knowledge of MLOps practices and model deployment pipelines
Understanding of natural language processing and information retrieval systems
Python
Familiarity with JavaScript/TypeScript for API integration
Experience with CUDA/GPU programming for model training
Preferred
Experience with SQL, Java, and statistical languages like R or Julia
Knowledge of database concepts and interaction with AI systems (PostgreSQL, MongoDB, Redis)
Experience with containerization (Docker) and orchestration (Kubernetes)
Familiarity with distributed computing frameworks (Spark, Ray)
Experience in educational technology or higher education settings
Publications or contributions to open-source AI projects