Conversational AI Engineer

Bright Vision Technologies is seeking a highly experienced Conversational AI Engineer with 10+ years of software engineering experience, including extensive expertise in Large Language Models (LLMs), agentic AI, and enterprise AI application development. The ideal candidate will define and lead the strategy, architecture, and engineering best practices for designing intelligent conversational systems, prompt engineering frameworks, and AI-powered applications. This role combines deep technical expertise in modern LLMs with the ability to build reusable AI platforms, evaluation frameworks, and developer tooling that enable scalable, secure, and production-ready conversational AI solutions., * Design, develop, and deploy enterprise-scale conversational AI applications powered by Large Language Models (LLMs).

• Define prompt engineering standards, reusable prompt libraries, and best practices for enterprise AI development.
• Architect and implement agentic AI workflows, multi-agent systems, tool orchestration, and Retrieval-Augmented Generation (RAG) solutions.
• Build scalable evaluation frameworks for prompt quality, hallucination detection, response accuracy, latency, and user experience.
• Develop reusable SDKs, APIs, and developer tooling that accelerate AI application development across engineering teams.
• Collaborate with product managers, AI researchers, software engineers, and business stakeholders to deliver production-ready AI solutions.
• Implement AI safety, Responsible AI, security, compliance, guardrails, and governance practices for enterprise deployments.
• Optimize LLM performance, inference efficiency, prompt execution, caching strategies, and operational scalability.
• Mentor engineers and establish engineering standards for conversational AI architecture, testing, deployment, and monitoring.
• Evaluate emerging LLMs, agent frameworks, and AI technologies to drive innovation and continuous platform improvement., *Telecommuting permitted: work may be performed within normal commuting distance from the Red Hat, LLC office in Raleigh, NC. Build backend systems with FastAPI (Python). Develop…
• 16 days ago +

• Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Machine Learning, Software Engineering, or a related technical discipline.
• 10+ years of professional software engineering experience, including significant experience building and deploying LLM-powered applications.
• Proven track record of delivering enterprise-scale conversational AI or LLM-based products in production.
• Deep expertise with modern LLM APIs and models such as OpenAI GPT, Anthropic Claude, Google Gemini, Llama, or Mistral.
• Strong experience with agent frameworks such as LangChain, LangGraph, LlamaIndex, Semantic Kernel, CrewAI, or AutoGen.
• Strong programming skills in Python and experience building scalable backend services and APIs.
• Experience implementing Retrieval-Augmented Generation (RAG), vector databases, embeddings, prompt engineering, and AI orchestration pipelines.
• Strong understanding of AI evaluation, model monitoring, observability, Responsible AI, and enterprise AI governance.
• Excellent communication, collaboration, analytical, and technical leadership skills., * Public technical writing, conference presentations, open-source contributions, or thought leadership in LLM application development.
• Experience designing multi-agent architectures, autonomous AI workflows, and complex tool-use systems.
• Familiarity with LLM fine-tuning, parameter-efficient tuning (LoRA/QLoRA), and model alignment techniques.
• Experience developing AI solutions for customer support, coding assistants, enterprise search, analytics, knowledge management, or business automation.
• Experience integrating conversational AI into enterprise applications with strict compliance requirements such as HIPAA, PCI-DSS, SOC 2, or FedRAMP.
• Experience with Kubernetes, MLOps, CI/CD pipelines, cloud platforms (AWS, Azure, or GCP), and production AI infrastructure.