Catapult Sports is hiring a Senior Agentic AI Engineer in New York, NY (onsite) to design and ship production-ready specialist AI agents and multi-agent orchestration for athlete performance intelligence. This role centers on confidence calibration, human-in-the-loop escalation, and measurable evaluation and observability so recommendations are fast, grounded, and escalation-aware.
Compensation: The target Total Compensation range for this position is $107,250 - $214,500 per year (inclusive of base salary and a target incentive plan, which may include equity, commission, or other bonus structures). Your specific compensation within this range is determined by factors such as geographic location, relevant experience, and job-related skills.
What you’ll build
- Specialist AI agents that use memory, tools, data, and multi-step reasoning.
- Multi-agent orchestration that routes work across specialist agents, manages dependencies, and synthesizes conflicting outputs.
- Systems that evaluate confidence, uncertainty, and consequence before recommendations reach a practitioner.
- Human-in-the-loop escalation patterns that determine when to answer, when to ask for more information, and when to defer to a human.
- Workflows that convert sport scientist expertise into validated, versioned, and testable agent capabilities.
- Evaluation, observability, and regression testing so agent performance can be measured and improved in production.
- Collaborations with domain experts to keep outputs grounded, traceable, and actionable.
What success looks like
- Specialist agents can investigate complex performance questions, use the right evidence, assess uncertainty, and produce recommendations practitioners can understand and trust.
- The system knows when not to answer.
- Every recommendation is Grounded. Calibrated. Traceable. Escalation-aware.
- The practitioner remains responsible, with the engineering work focused on making decisions better informed, faster, and more defensible.
Requirements
- Experience personally shipping a production agentic AI system used by real users.
- Hands-on experience with memory or persistent state.
- Hands-on experience with tool use or tool calling.
- Hands-on experience with multi-step reasoning or workflows.
- Hands-on experience with production deployment and operation.
- Built or substantially contributed to a production multi-agent system.
- Understanding of agent routing and orchestration, specialist agent composition, and dependency-aware workflows.
- Understanding of parallel and sequential execution, conflicting agent outputs, and response synthesis.
- Comfort calibrating probabilistic ML or AI systems, including familiarity with Platt scaling, isotonic regression, and Expected Calibration Error (ECE).
- Comfort with reliability and calibration curves, confidence and uncertainty estimation.
- 5+ years of professional experience in applied ML, AI, or software engineering.
- Strong Python and strong software engineering fundamentals.
- Experience building and operating production systems.
- Experience with production RAG and reranking.
- Experience with foundation-model fine-tuning or domain adaptation, including LoRA and PEFT or similar techniques.
- Experience with LLM observability and drift detection.
- Experience with evaluation harnesses and automated regression testing.
- Experience with human-in-the-loop architectures, confidence thresholds, and escalation models.
- Experience with causal or counterfactual reasoning.
- Experience with Go/Golang.
- Experience with AWS, including ECS, EC2, Lambda, SNS or SQS.
- Experience with GraphQL, REST or gRPC.
- Experience with PostgreSQL or MongoDB.
- Experience working with sport scientists, clinicians, or other domain experts is a plus.
- Familiarity with athlete performance data such as workload, readiness, recovery, biomechanics, or athlete performance data will help.
- Framework experience such as LangGraph, AutoGen, CrewAI, or equivalent is valuable.
Technologies
Python, LangGraph, AutoGen, CrewAI, Platt scaling, isotonic regression, Expected Calibration Error (ECE), LoRA, PEFT, Go/Golang, AWS, ECS, EC2, Lambda, SNS, SQS, GraphQL, REST, gRPC, PostgreSQL, MongoDB
Benefits
- Generous paid leave and recognized company holidays.
- Health, Dental, and Vision insurance.
- 401(k) retirement plan with company match.
- Opportunity to participate in Catapult Sports’ comprehensive benefits package.
Before you apply
- Production agentic AI.
- Production multi-agent orchestration.
- Hands-on confidence calibration.
We don’t expect every candidate to have every preferred skill. If you have the core experience and are excited by the problem, apply.
All offers of employment are subject to Catapult’s positive prehire check. To find out more, contact the Talent Partner for this role.
