Senior Artificial Intelligence Specialist (AI)

Location: Europe; remote

Company

hirify.global_TECH builds B2B iGaming platforms for operators, providing integrations, consulting, and long-term operational support for platforms serving millions of active players.

What you will do

• Design, build, and operate production-grade AI agent infrastructure and services on AWS.
• Develop agent orchestration, stateful workflows, durable execution, checkpointing, retries, and failure recovery.
• Build MCP-based integrations, secure tool execution, reusable platform components, APIs, and SDKs.
• Design scalable and fault-tolerant AI services with LLM gateways, model routing, fallbacks, cost controls, observability, tracing, and evaluation.
• Optimize performance, latency, scalability, and infrastructure costs while owning solutions from architecture through production support.
• Implement authentication, authorization, access controls, human-in-the-loop approvals, and engineering standards for secure and reliable AI systems.

Requirements

• 5+ years of software engineering experience, including strong Python backend expertise.
• Proven experience building and operating LLM-powered systems in production.
• Hands-on experience with agent orchestration frameworks such as LangGraph or similar, LLM APIs, tool/function calling, and agentic workflows.
• Strong understanding of distributed systems, asynchronous processing, and fault tolerance.
• Experience with Python type safety, data validation, and schema management using Pydantic or an equivalent.
• Experience with cloud infrastructure, preferably AWS, Docker, and CI/CD.
• Understanding of API security, authentication, and authorization.
• Strong engineering fundamentals in system design, testing, debugging, and observability.
• Ability to independently design, implement, and operate complex technical components.

Nice to have

• Production experience with LangGraph and LangChain.
• Experience with MCP servers, clients, gateways, and tool integration infrastructure.
• Experience with durable workflows, checkpointing, distributed state management, LLM gateways, model routing, caching, and inference optimization.
• Experience with agent evaluation, tracing, and observability using MLFlow, Langfuse, or OpenTelemetry.
• Experience with Kubernetes, EKS, event-driven architectures, and platform engineering.
• Experience with agent security, sandboxing, human-in-the-loop workflows, RAG architectures, and vector databases.

Culture & Benefits

• Remote-first work with technical support and coworking compensation.
• Annual benefits budget for sports, medical care, mental health, home office, and languages.
• Paid maternity and paternity leave, monthly childcare allowance, 20+ vacation days, unlimited sick leave, and emergency time off.
• Online, offline, and offsite team events.
• Internal courses, growth programs, open feedback, experimentation, and a culture based on trust, ownership, resilience, and continuous learning.