AI Applications Engineer

Summary The firm is seeking an AI Engineer to help develop and improve artificial intelligence applications, including systems built around large language models and retrieval pipelines. The role focuses on implementing and enhancing clearly defined features within existing AI platforms while contributing to experimentation, system design, and production deployment. This position sits within the Practice Innovation team and works closely with Legal Engineering, Practice Solutions, Knowledge Management, and Cloud/Infrastructure teams to deliver scalable AI capabilities across the organization. Responsibilities Develop and improve AI-powered applications, including retrieval-based systems, supporting data pipelines, and workflow-driven tools. Build and refine AI agents that coordinate multi-step processes and integrate with internal tools used in legal workflows. Apply modern retrieval-augmented generation approaches to improve system performance, reliability, and output accuracy. Run structured testing and evaluation to improve prompts, retrieval strategies, agent behavior, and model responses. Contribute to processes for ingesting, organizing, cleaning, and indexing data used by AI applications. Assist with deployment, monitoring, and iterative improvement of AI systems running in production environments. Take responsibility for clearly scoped features and help move them from design through implementation and deployment. Work with infrastructure and cloud teams to support secure and scalable system deployment. Skills & Abilities Experience building applications powered by large language models in production or near-production environments. Familiarity with vector databases and semantic search technologies such as Qdrant, Pinecone, Weaviate, or comparable tools. Understanding of retrieval-augmented generation architectures and strategies for improving retrieval performance. Experience working with both structured and unstructured data sources. Strong programming skills in Python and solid software engineering fundamentals, including testing and maintainable code practices. Familiarity with cloud environments such as AWS, GCP, or Azure, as well as containerization tools including Docker or Kubernetes. Strong analytical and problem‑solving capabilities. Ability to work independently on defined tasks while escalating issues when appropriate. Effective communication skills and the ability to collaborate with both technical and non-technical stakeholders. Experience Bachelor’s degree in Computer Science, Engineering, or a related technical discipline. At least two years of experience in software engineering, machine learning, artificial intelligence, or a closely related field. Preferred Experience deploying AI agents or large language model–based systems in production environments. Experience working with Azure cloud services. Familiarity with monitoring, logging, and evaluation methods for AI systems operating in production. Experience working within enterprise or regulated environments. Salary $125,000 – $145,000, plus Bonus Along with base pay and potential bonus opportunities, the firm provides a comprehensive benefits program that may include paid leave, medical, dental, and vision coverage, a 401(k) retirement plan, and discounted memberships to select fitness facilities. This role is based in the firm’s New York office and presently follows a hybrid work arrangement, which may be adjusted in the future. The anticipated compensation range is between $125,000 and $145,000 annually, with eligibility for a performance-based bonus. Final compensation will depend on several considerations, such as the candidate’s experience, professional qualifications, education, skill set, and any relevant licenses or certifications, as well as broader market conditions and internal firm guidelines. Salary: $125,000 – $145,000 Date Active: 3/14/26 Exempt/Not Exempt: Exempt #J-18808-Ljbffr Considine Search