AI Engineer

Open Access Technology International (OATI) is seeking AI Engineers with hands-on experience building and deploying production AI solutions. These positions offer the opportunity to work on cutting edge technologies, including Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), multi-agent systems, Model Context Protocol (MCP) integrations, and advanced machine learning applications.Our team is solving complex challenges in electric power system operations by applying AI technologies to forecasting, optimization, reliability, anomaly detection, decision support, and intelligent automation, leveraging decades of industry-leading operational data.

Responsibilities

Conduct research, development, and implementation of AI solutions for power system operations, utilizing OATI's extensive datasets to address forecasting, optimization, anomaly detection, reliability, and operational challenges.Design, build, deploy, and support enterprise-grade AI solutions leveraging Generative AI, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and agentic AI frameworks.Design and implement multi-agent systems, including agent orchestration, Model Context Protocol (MCP) integrations, and autonomous decision-making workflows.Develop, fine-tune, evaluate, and optimize foundation models, neural networks, and machine learning solutions for energy industry applications.Build scalable retrieval and knowledge management pipelines to ensure accurate, grounded, and context-aware AI responses.Establish and maintain best practices for AI architecture, MLOps, model monitoring, observability, and governance.Analyze large-scale operational data to develop predictive, optimization, and decision-support capabilities.Collaborate with researchers, software engineers, data scientists, and business stakeholders to deliver production-ready AI solutions.Contribute to technical design, code development, documentation, and knowledge sharing across the organization.Education:Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Machine Learning, or a related field; PhD preferred.

Technical Skills

3-5 years of hands-on experience designing, building, deploying, and supporting AI-powered solutions utilizing LLMs, RAG, and agentic AI architectures.Strong Python programming skills and experience developing production applications using modern AI/ML frameworks.Demonstrated experience implementing, optimizing, and evaluating LLM solutions, including fine-tuning, prompt engineering, and model evaluation.Hands-on experience designing and deploying production RAG systems, vector databases, and retrieval technologies, including hybrid search, BM25, sparse and dense vectors, embeddings, and ranking techniques.Experience building and fine-tuning foundation models (LLMs, multimodal models, and transformer-based architectures) for real-world business applications.Hands-on experience designing, implementing, and supporting multi-agent AI systems, including orchestration, agent memory management, agent-to-agent communication, and MCP integrations.Experience developing, deploying, and optimizing machine learning and deep learning solutions using frameworks such as PyTorch and TensorFlow.Experience establishing AI operational best practices, including MLOps, model monitoring, observability, and governance.Strong understanding of AI evaluation methodologies, performance measurement, hallucination mitigation, and model validation techniques.Strong problem-solving skills with the ability to communicate technical concepts and architecture decisions to both technical and business stakeholders.Experience with NLP pipelines, conversational AI solutions, and data engineering concepts.Proficiency with Git, SQL, and NoSQL database technologies.Experience with AI security, compliance, and responsible AI practices.Relevant Project ExperienceExperience designing, developing, deploying, and supporting AI-powered solutions in production environments.Ability to describe AI architectures personally implemented, including design decisions, technology selection, evaluation methodology, and operational support.Experience working on enterprise AI, machine learning, or automation projects from concept through deployment.Required Hands-On ExperienceCandidates must be able to discuss AI solutions they have personally designed, built, deployed, and supported, including:RAG architectures and retrieval optimizationHybrid search (BM25, sparse and dense vectors, vector databases)Multi-agent systems and orchestrationAgent memory and context managementMCP implementation and integrationsAI evaluation and hallucination mitigationFine-tuning using LoRA, QLoRA, or similar techniquesProduction deployment, monitoring, and troubleshooting of AI solutions