Catapult is a sports technology company advancing performance analytics. We are looking for an Agentic AI Engineer to design and build the AI layer that enables coaches and athletes to access calibrated, escalation-aware insights. You will create specialist agents, the workflow engine that encodes domain expert knowledge into validated agent skills at scale, and the decision intelligence layer that translates agent outputs into calibrated, actionable recommendations. Building an agent is not the hard part; making an agent trustworthy—calibrated, grounded, escalation-aware, and provenance-traced—is the standard we demand. If you have shipped production agentic AI systems (not just demos) and care deeply about earning trust rather than just predicting, this is the role for you. What you’ll need: 5+ years in applied ML or AI engineering with at least 2 years building production agentic AI systems; deep experience with multi-agent frameworks and orchestration; hands-on experience with confidence calibration and evaluation for probabilistic systems; production retrieval-augmented generation with reranking; experience fine-tuning foundation models for domain knowledge; strong Python and Golang; experience with LLM observability and drift detection; familiarity with AWS services, GraphQL/REST/gRPC, Postgres and Mongo. Preferred: knowledge acquisition workflows, collaboration with domain scientists, human-in-the-loop architectures, sports science familiarity, and causal or counterfactual reasoning. Your success will be measured by systems that know when they don’t know and escalate

Catapult is a sports technology company advancing performance analytics. We are looking for an Agentic AI Engineer to design and build the AI layer that enables coaches and athletes to access calibrated, escalation-aware insights. You will create specialist agents, the workflow engine that encodes domain expert knowledge into validated agent skills at scale, and the decision intelligence layer that translates agent outputs into calibrated, actionable recommendations. Building an agent is not the hard part; making an agent trustworthy—calibrated, grounded, escalation-aware, and provenance-traced—is the standard we demand. If you have shipped production agentic AI systems (not just demos) and care deeply about earning trust rather than just predicting, this is the role for you. What you’ll need: 5+ years in applied ML or AI engineering with at least 2 years building production agentic AI systems; deep experience with multi-agent frameworks and orchestration; hands-on experience with confidence calibration and evaluation for probabilistic systems; production retrieval-augmented generation with reranking; experience fine-tuning foundation models for domain knowledge; strong Python and Golang; experience with LLM observability and drift detection; familiarity with AWS services, GraphQL/REST/gRPC, Postgres and Mongo. Preferred: knowledge acquisition workflows, collaboration with domain scientists, human-in-the-loop architectures, sports science familiarity, and causal or counterfactual reasoning. Your success will be measured by systems that know when they don’t know and escalate