Lead Software Engineer - RAG System Development

We are excited to invite a passionate Lead Software Engineer to join our dynamic team focused on building an advanced healthcare-oriented Retrieval-Augmented Generation (RAG) system. This groundbreaking system integrates document retrieval and response generation to provide precise and context-sensitive answers. As a key member of our team, you will design, implement, and maintain end-to-end RAG pipelines, manage interactions with language models (LLMs), create APIs, and ensure the smooth, secure delivery of knowledge-driven capabilities. In this collaborative environment, you'll have the opportunity to shape the Next Generation Health Solutions through innovative technology. Key Responsibilities: Architect, implement, test, and operate comprehensive RAG workflows. Ingest and normalize documents from a variety of sources. Generate and manage embeddings; index and query vector databases to retrieve relevant passages, apply reranking or fusion strategies, and prepare prompts for LLMs. Build scalable, low-latency services and APIs (Python is preferred; familiarity with other languages is welcome) to ensure high production-grade reliability, including monitoring, tracing, and alerting. Integrate with vector databases and embedding pipelines, optimizing for latency, throughput, and cost efficiency. Design and implement MLOps workflows, focusing on model management, experimentation, feature stores, CI/CD for machine learning services, and rollback strategies. Develop efficient data pipelines with governance mechanisms for ingestion, provenance tracking, quality assurance, and access control. Work closely with data engineers to enhance retrieval quality through advanced embedding techniques, reranking, cross-encoder models, and prompt engineering, while implementing evaluation metrics such as precision/recall and QA accuracy. Establish comprehensive monitoring and observability measures for RAG components, including tracking latency, success rates, cache effectiveness, retrieval quality, and data drift. Implement stringent security, privacy, and compliance protocols (e.g., authentication, authorization, data masking, handling of PII, and audit logging). Required Qualifications: A minimum of 5 years of professional experience in software engineering, focusing on the design and delivery of production systems. Strong programming expertise in Python (NodeJs knowledge is a plus). In-depth understanding of retrieval-augmented and application-scale NLP systems with hands-on experience in building RAG-like pipelines. Familiarity with MLOps tools and concepts for effective machine learning workflow management. Proficiency in cloud infrastructure and modern software practices (AWS/GCP/Azure; Docker; Kubernetes; CI/CD). Exceptional problem-solving skills, strong communication abilities, and a proven track record of collaborating with cross-functional teams. Knowledge of data governance, privacy, and security best practices. Preferred Qualifications: Experience with agentic workflow tools and prompt engineering for LLMs. Exposure to various LLMs and their evaluation methodologies. Ability to conduct A/B testing and create dashboards for evaluation metrics in retrieval and QA systems. Expertise in data processing frameworks (SQL, Pandas, Spark) and large-scale data pipelines. Background in performance optimization for low-latency AI services. Experience with monitoring tools and techniques. Ability to minimize token usage and optimize costs effectively. Proficient in designing and implementing security controls for data-intensive AI systems. Join Elsevier, a leader in scientific, technical, and medical research analytics, and play an integral role in shaping healthcare solutions through technology. We offer a competitive base pay range, along with a variety of benefits tailored to support your well-being and career growth. Please be aware that we are committed to creating an inclusive and equitable hiring process. If you require assistance or adjustments during the application process, please inform us. We prioritize security and do not request any personal financial information from candidates. We value your privacy and adhere to our Candidate Privacy Policy. Elsevier is an equal opportunity employer and embraces diversity in the workforce.

Created: 2026-03-07