The Role This is a 70% hands-on coding and 30% leverage of Claude and AI tools role. You will build shared services (across 6 Engineering teams), platform automation, and prototypes.

------------------------------------------------------------------------

------------------------------------------------------------------------

Compensation: $180,000–$210,000 base + 10% bonus + full benefits

Location: 100% Remote Client: Sports & Entertainment Ticket Data Leader

About the Role

Python is your primary language, with TypeScript/Node.js as a strong secondary. You’ll own the AI backend and the data/retrieval layers behind it, partnering with dedicated frontend engineers (Next.js / React). We care less about which specific libraries you’ve used and far more about how you think — about tradeoffs, reliability, evaluation, and what it takes to run AI in production.

Core Qualifications: AI Engineering

The heart of the role. We hire for AI-first capability demonstrated through production work.

• LLM orchestration & prompt systems: Deep, hands-on experience with LLM APIs (Anthropic/Claude, OpenAI). Complex prompt chains, structured extraction, reliable behavior on probabilistic models, fluency in token economics, and latency tradeoffs.
• RAG & vector databases: Production RAG experience including chunking, embeddings, retrieval-quality tuning, and hybrid search over pgvector and OpenSearch.
• Agentic systems & frameworks: AI systems that act — tool-use patterns, Model Context Protocol (MCP), agent frameworks (e.g., Strands Agents, AWS Bedrock AgentCore), and AWS Bedrock for managed model access.
• AI proxy & governance layers: Experience with AI proxy/gateway layers for routing, rate limiting, cost control, and governance of LLM traffic across an organization.
• Evaluation & feedback loops: Systematic LLM evaluation — measuring quality, catching regressions, and closing the loop so systems improve over time. You know when to reach for prompt engineering vs. RAG vs. fine-tuning and can defend your choices.
• Production AI pipelines: End-to-end pipelines (ingestion through inference and post-processing) that are modular, observable, and built to run reliably at scale.

About the Company

We are the technology backbone of the North American secondary ticketing market. Thousands of sellers rely on our automation, pricing intelligence, and platform infrastructure to operate at scale.

AI is now central to how we move the business forward. We are building AI-native platform capabilities from the ground up: governed LLM systems, retrieval over our proprietary event and pricing data, and agentic services that take real action across our products.

This is a deliberate investment in an intelligence layer that becomes a durable competitive advantage — not an “AI initiative” bolted onto a legacy stack. If you want to define how a serious company applies AI in production, this is the place.

What You’ll Do

This role is measured by impact. The intelligence you build will power both customer-facing products and the operational core of the business.

• Define and ship AI systems: Multi-step LLM workflows, RAG over proprietary data, and agentic services that take action — built reliably on top of non-deterministic models.
• Deliver impact for operations: Translate operational problems into AI-powered and data-driven systems that make teams faster and decisions sharper (this is core to the role).
• Own evaluation and the feedback loop: Stand up eval pipelines and feedback mechanisms that let us ship AI with confidence and improve it continuously (quality measurement, regression detection, observability).
• Set the engineering patterns: How we orchestrate models, structure retrieval, proxy and govern LLM traffic, and keep probabilistic systems reliable at scale.

Core Qualifications: Operations & Impact

This role bridges engineering and operations. Delivering operational impact is central to how you’ll be valued.

• Operational impact: Proven record translating business and operational needs into systems — reporting, dashboards, and internal tools that drive efficiency and visibility for product and operations stakeholders.
• Data pipelines & transformation: Designing pipelines that aggregate and transform structured and unstructured data from multiple sources, including modeling with dbt.
• Solo / startup experience: Comfortable flying solo in a startup environment — owning problems end-to-end, scoping your own work, and shipping without heavy process or hand-holding.
• Stakeholder collaboration: Work directly with non-technical stakeholders to identify friction points and ship practical solutions.

Core Qualifications: Engineering Foundations

• Python (primary): Clean, testable, production-grade code with deep FastAPI experience.
• TypeScript & Node.js: Production experience (Express, NestJS, or similar).
• APIs: Designing, building, and consuming RESTful APIs; integrating third-party services.
• Databases: PostgreSQL, MySQL; non-relational stores (Elasticsearch/OpenSearch, MongoDB, Redis) used appropriately.
• Cloud & infrastructure: Deploying and operating on AWS with Docker and Kubernetes (EKS).
• Microservices: Sound instincts for service boundaries, inter-service communication, and distributed systems operations.

Nice to Have

• ML / MLOps: scikit-learn, PyTorch, or TensorFlow; experiment tracking (MLflow, Weights & Biases); model serving and monitoring.
• Orchestration & streaming: Airflow or Dagster; Kafka or Kinesis.
• Event-driven & observability: RabbitMQ/Kafka; Datadog, Sentry, or similar APM tools.
• Domain experience: Ticketing, live events, or e-commerce; launching new products to market.

Education & Experience

• 5+ years in software development, with demonstrable production experience applying LLM-based systems and RAG pipelines in a real business context.
• B.S. in Computer Science, Machine Learning, or a related field (or commensurate experience), including a strong portfolio (e.g., GitHub).