Senior AI Engineer

League Inc.

About The Position

We are seeking a Senior AI Engineer to join our AI & Data Group on the AI Orchestration team. This role is responsible for designing, building, operating and scaling the orchestration layer that powers League’s AI-driven healthcare experiences. Sitting at the intersection of AI systems design, ML productionization, and distributed software engineering, you will take the probabilistic capabilities of large language models and engineer them into reliable, measurable, and scalable product experiences. This is a hands-on senior engineering role for a practitioner who moves beyond prototypes to own the hard problem of making AI work at scale. You will translate leading edge AI innovation into reliable, secure, and compliant systems. Your work will directly impact how AI is operationalized across League’s digital health ecosystem—ensuring systems are scalable, observable, performant, and safe in a regulated environment.

Requirements

Deep Technical Expertise: Extensive hands-on experience in software engineering and a strong understanding of the entire machine learning lifecycle
Platform-Level Thinking: Proven ability to design and build scalable, distributed systems, ideally for machine learning or data-intensive applications
MLOps Mastery: Demonstrated experience with MLOps tools and practices, including CI/CD for machine learning, model versioning, and feature stores
Cloud Proficiency: Expertise with public cloud platforms (e.g., AWS, GCP, Azure) and a solid understanding of containerization and orchestration technologies like Docker and Kubernetes
Data Fluency: A strong grasp of data engineering concepts, including data pipelines, data warehousing, and distributed data processing frameworks

Nice To Haves

Programming Languages: familiarity with Go for backend services is a bonus.
Data Systems: Experience with vector databases (Pinecone, ChromaDB, Mongo) and retrieval strategies (chunking, hybrid search, re-ranking) a definite bonus

Responsibilities

AI Orchestration & Systems Design Design and build production-grade AI systems, including RAG pipelines, multi-step agents, and LLM-powered features.
Make principled architecture choices regarding RAG vs. fine-tuning and agentic loops vs. simpler call-and-response patterns.
Architect for long-term maintainability, ensuring systems fail gracefully and handle non-deterministic outputs predictably.
Evaluation & Quality Assurance Build comprehensive evaluation and observability frameworks to measure model accuracy, grounding, and quality drift.
Implement automated test suites and "LLM-as-judge" pipelines to catch defects before they reach production.
Set quality standards for AI components and drive improvements based on human feedback loops.
Production Engineering & MLOps Create production-quality Python services to wrap AI logic into secure microservices.
Leverage AI coding assistants (Claude Code, Codex, Cursor, etc) to write the majority of your code, while still retaining ownership and deep understanding of the product created
Own the model lifecycle, including versioning prompts as first-class code artifacts and monitoring for performance degradation.
Manage the economics of LLM usage, balancing model performance against latency and cost
Collaboration & Technical Leadership Partner with Product, Data Science, and Backend teams to translate ambiguous requirements into technical specifications.
Mentor junior engineers on AI craft, including embedding selection, vector store design, and prompt engineering precision.
Actively reduce knowledge concentration by contributing to shared AI tooling and documentation.
Contribute to roadmap planning and longer-term AI architecture decisions.
Platform Excellence & Innovation Establish and uphold standards for performance, security, privacy, and data governance within AI systems.