Join Optum, a global leader in health optimization, and drive advancements in AI/ML. We're seeking a Senior AI/ML Engineer to develop cutting-edge AI features that improve health outcomes for millions. Our inclusive culture fosters collaboration, professional growth, and comprehensive benefits. Contribute to a mission that connects people with essential care and resources, making a significant impact on communities worldwide. Start your journey with us to Care, Connect, and Grow together.

This role is instrumental in building and refining Large Language Model (LLM) based applications, including chat functionalities, summarization tools, knowledge search, and data extraction systems. You will leverage prompt engineering techniques and explore advanced model tuning methods like LoRA, while also implementing robust RAG workflows.

Develop and enhance LLM-driven features such as chat, summarization, knowledge search, and data extraction. Apply advanced prompt engineering and support model fine-tuning or parameter-efficient tuning (e.g., LoRA). Implement RAG (retrieval augmented generation) workflows, including preprocessing, embedding generation, and vector search. Work with transformer-based models, applying a deep understanding of attention, embeddings, and model behavior. Assist in model interpretability and enhance the reliability of model outputs. Improve AI accuracy by reducing hallucinations through effective prompting, guardrails, and retrieval enhancements. Support benchmarking, evaluation tests, and quality assurance checks for AI models. Contribute to the development and implementation of Responsible AI practices. Build services that integrate AI APIs from providers like OpenAI, Azure, and open-source LLMs. Implement tool/agent orchestration flows, collaborating with senior team members for guidance. Utilize vector databases such as FAISS, Pinecone, or pgvector for efficient data management. Contribute to performance enhancements, focusing on latency, throughput, and token efficiency. Support the implementation of model compression and quantization techniques. Develop caching and batching strategies to optimize system performance. Collaborate closely with product, data, and engineering teams to deliver high-quality AI features. Participate actively in code reviews, team design discussions, and knowledge sharing sessions.

A Bachelor's or Master's degree in Computer Science, Engineering, or a related discipline is required. Possess at least 5 years of software engineering experience, with a minimum of 1-2 years focused on generative AI or LLMs. Experience in building scalable cloud-based applications using Azure, AWS, or GCP is essential. Demonstrate working knowledge of LLMs, prompt engineering, model fine-tuning basics, and RAG principles. Solid understanding of Transformer architecture fundamentals, including attention mechanisms and embeddings. Familiarity with evaluation and safety concepts, such as hallucination reduction and quality checks. Experience with AI integration using APIs, vector databases, and orchestration frameworks. Knowledge of token optimization and latency reduction strategies. Proficiency in Python or TypeScript is mandatory. Proven ability to solve complex problems and strong collaborative skills are crucial for this role.