MLOps Engineer

Would you like to perform rewarding work while contributing to the success of an established, growing company? Join our innovative team as an MLOps Engineer and drive the seamless integration and deployment of machine learning models into production environments! We are looking for a skilled MLOps Engineer to collaborate with data scientists, software engineers, and operations teams to build, deploy, and maintain scalable ML pipelines and infrastructure that power cutting-edge AI solutions. Qualifications: Bachelor's degree in Computer Science, Engineering, Artificial Intelligence, Data Science, or a related field. Minimum 6+ years of experience in AI, Machine Learning, or Software Engineering, with strong expertise in Large Language Models (LLMs). Strong proficiency in Python and experience designing and developing enterprise-grade AI applications. Proven experience deploying, fine-tuning, and optimizing open-source LLMs using techniques such as LoRA, QLoRA, or PEFT. Strong experience designing advanced Retrieval-Augmented Generation (RAG) solutions, including chunking strategies, retrieval optimization, re-ranking, and grounding techniques. Hands-on experience with AI orchestration frameworks such as LangChain, LangGraph, CrewAI, or similar technologies. Experience optimizing LLM inference using vLLM, Quantization, Batching, KV Cache, or similar performance optimization techniques. Experience with Docker, Kubernetes, MLflow, and cloud platforms, preferably AWS. Strong understanding of software architecture, microservices, and scalable AI platform design. Excellent communication, mentoring, and technical leadership skills. Responsibilities: Design and develop enterprise-scale LLM solutions and AI-powered applications aligned with business needs. Lead the architecture and implementation of scalable RAG solutions, continuously improving retrieval quality and response accuracy. Deploy, optimize, and manage self-hosted LLMs in production environments, ensuring high performance and scalability. Define architectural standards and best practices for LLM development, model serving, and AI application design. Improve inference performance through GPU optimization, batching, quantization, and modern LLM serving techniques. Collaborate with cross-functional teams to integrate AI capabilities into enterprise applications and microservice architectures. Mentor engineers, provide technical guidance, and support the adoption of AI engineering best practices across development teams. Evaluate emerging AI technologies, frameworks, and models, recommending innovative solutions that align with business objectives. OBSS is proud to be an equal opportunity workplace and is an affirmative action employer. We make recruiting decisions without regard to race, color, religion, national or ethnic origin, age, gender, sexual orientation, marital status, veteran status or disability status. https://medium.com/codable