Agentic AI Engineer

Описание

This role involves designing and shipping specialist AI agents, building multi-agent orchestration, and developing systems for confidence evaluation and human-in-the-loop escalation.

Responsibilities

• Design and ship specialist AI agents that use memory, tools, data and multi-step reasoning
• Build multi-agent orchestration that routes work between specialist agents, manages dependencies and synthesises conflicting outputs
• Develop systems that evaluate confidence, uncertainty and consequence before recommendations reach a practitioner
• Build human-in-the-loop escalation so the system knows when to answer, when to ask for more information and when to defer to a human
• Create workflows that turn sport scientist expertise into validated, versioned and testable agent capabilities
• Build evaluation, observability and regression testing so agent performance can be measured and improved in production
• Work with domain experts to ensure AI outputs are grounded, traceable and actionable

Requirements

• Production agentic AI
• Memory or persistent state
• Tool use or tool calling
• Multi-step reasoning or workflows
• Production deployment and operation
• Chatbots, prompt engineering and RAG alone are not enough
• Multi-agent orchestration
• You have built or substantially contributed to a production multi-agent system
• Agent routing and orchestration
• Specialist agent composition
• Dependency-aware workflows
• Parallel and sequential execution
• Conflicting agent outputs
• Response synthesis
• Confidence calibration
• You have hands-on experience calibrating probabilistic ML or AI systems
• Platt scaling
• Isotonic regression
• Expected Calibration Error (ECE)
• Reliability and calibration curves
• Confidence and uncertainty estimation
• 5+ years of professional experience in applied ML, AI or software engineering
• Strong Python
• Strong software engineering fundamentals
• Experience building and operating production systems
• Experience with Production RAG and reranking
• Foundation-model fine-tuning or domain adaptation
• LoRA, PEFT or similar techniques
• LLM observability and drift detection
• Evaluation harnesses and automated regression testing
• Human-in-the-loop architectures
• Confidence thresholds and escalation models
• Causal or counterfactual reasoning
• Go/Golang
• AWS, including ECS, EC2, Lambda, SNS or SQS
• GraphQL, REST or gRPC
• PostgreSQL or MongoDB

Nice to have

• Experience with LangGraph, AutoGen, CrewAI or equivalent frameworks is valuable
• Experience working with sport scientists, clinicians or other domain experts is a plus
• You don't need to be a sports scientist, but familiarity with workload, readiness, recovery, biomechanics or athlete performance data will help

We offer

• Customer location: USA
• Working hours - 11.00-20.00 CET (>50% overlap with New York)
• Language: English B2+
• Estimated start date: 16.11.2026
• Duration: 12 months

Hiring process

• Писать ••• С РЕЗЮМЕ В КОТОРОМ УКАЗАН ВОЗРАСТ И ЛОКАЦИЯ НАХОЖДЕНИЯ
• Укажите 🆔 вакансии
• Без этой информации отклики не рассматриваются