BWX Technologies, Inc. is looking to solve complex business processes through the design, build, deployment and maintenance of intelligent, multi-step workflows and conversational systems using Generative AI.
Requirements
- Hands-on experience deploying and managing AI/ML solutions within the Microsoft Azure platform including (but not limited to) Azure OpenAI Service and Azure AI Search / Cognitive Search.
- Proven experience building workflow automations or orchestration using tools such as n8n, Logic Apps, or equivalent.
- Solid programming skills in Python, and experience with APIs, data pipelines and integration of external services.
- Familiarity with containerization (Docker) and orchestration technologies (Kubernetes / AKS) in enterprise production environments.
- Experience with CI/CD, GitOps or MLOps practices for model deployment and lifecycle management.
- Strong understanding of Natural Language Processing (NLP), Large Language Models (LLM), Retrieval-Augmented Generation (RAG), prompt engineering and related techniques.
- Experience working with open-source generative AI frameworks such as Ollama, LangChain, LlamaIndex, or Hugging Face model ecosystems.
Responsibilities
- Leads the design and implementation of autonomous, multi-step AI agents (workflows) that leverage LLMs + orchestration to automate complex business processes (e.g., research automation, document processing, data synthesis).
- Creates workflow automations using orchestration tools such as n8n (or equivalents), connecting APIs, event triggers, data sources, and AI models into end-to-end solutions.
- Develops, deploys and manages Generative AI solutions using both cloud and open-source ecosystems: e.g., Microsoft Azure services (Azure OpenAI Service, Azure AI Search / Cognitive Search, Azure Machine Learning, Azure Functions) and open-source frameworks (e.g., Ollama, LangChain, LlamaIndex, Hugging Face stacks).
- Contributes to the design and implementation of conversational AI systems (chatbots, virtual assistants) capable of business-task execution and user-interaction.
- Applies advanced prompt engineering, fine-tuning, RAG (Retrieval-Augmented Generation) architectures and model-optimization techniques to ensure high performance, accuracy and reliability of deployed agents.
- Collaborates with data scientists, business analysts, product owners and engineering teams to integrate AI workflows into enterprise systems, aligning with business objectives and user needs.
- Establishes testing, monitoring, optimization and governance frameworks for AI agents — covering performance metrics, reliability, bias-mitigation, ethical AI compliance and scalability.
Other
- Bachelor’s degree in Computer Science, Information Systems, or a related discipline.
- At least 3 years of professional experience in software development, AI/ML engineering or data science — of which at least 1 year must be focused on Generative AI or LLM-based applications.
- Must be a U.S. citizen with no dual citizenship.
- Must be able to obtain and maintain a U.S. Department of Energy (DOE) clearance.
- Excellent communication skills with the ability to present complex technical concepts in business-friendly language and collaborate across functional teams.
