AI Engineer

Responsibilities

• Continuous LLM Evaluation: Design and operate a systematic, ongoing process to evaluate new and emerging LLMs across accuracy, relevancy, speed, and cost — continuously benchmarking them against the specific tasks in our orchestration pipeline proactively optimizing outcomes
• Eval Framework Development: Build and maintain rigorous evaluation frameworks (Evals) to measure LLM output accuracy, relevance, faithfulness, and speed with a specific focus on reducing hallucinations in medical record summarization and legal document analysis
• Proactive Model Transition Planning: Monitor the LLM landscape across providers to identify deprecation timelines and suitable replacement models — and own the full execution of those transitions, including integrating new models into the production pipeline and maintaining necessary changes to account for model behavior
• AI Pipeline Optimization: Directly implement optimizations to LLM-based orchestration pipelines for document understanding, medical record summarization, case chronology generation, and drafting support — owning code changes, deployments, and production validation from start to finish
• Cross-Functional Collaboration: Partner with product and GTM stakeholders to communicate model evaluation findings — then lead the technical implementation yourself rather than delegating execution to a separate engineering team
• End-to-End Implementation Ownership: Take full responsibility for shipping model changes into production — writing the integration code, managing deployments, running validation tests, and ensuring a clean rollout
• Operational Monitoring: Implement monitoring and observability for model performance in production, benchmarking outputs and cost, detecting drift with ongoing and continuous reporting to management
• Documentation: Maintain thorough documentation of evaluation methodologies, model comparison results, transition decisions, and runbooks for the systems you own

Requirements

• 5+ years of AI/ML engineering experience evaluating, fine-tuning, and deploying large language models in production environments — including building and deploying the models to cloud (AWS or GCP) infrastructure at scale
• Hands-on development and implementation of multiple RAG solutions
• Hands-on experience leveraging embedding models and vector databases
• Hands-on experience building agentic workflows
• Deep familiarity with the LLM ecosystem and the ability to critically assess model capabilities, limitations, and fit for specific tasks, including cost, quality, speed, and capability tradeoffs. Proven experience designing and operating evaluation frameworks to measure LLM output quality, including accuracy, relevancy, and hallucination detection in high-stakes domains (legal, medical, or similar)
• Strong software engineering foundation with proven experience writing production-deployed solutions, including LLM orchestration frameworks and multi-model pipelines
• Comfort working in a fast-paced, high-ambiguity environment with strong ownership, tight feedback loops, and a bias for systematic process-building over one-off fixes
• Excellent communication skills; ability to translate complex model evaluation findings into clear recommendations for engineering, product, and non-technical stakeholders
• Bonus: experience with unstructured medical or legal document processing, or background in classical ML (statistics, embeddings, retrieval-augmented generation)