Leads the team this role joins
Decides on early hires
Runs hiring at the company
From your own Gmail and LinkedIn.
About the role
A remote, full-time senior role for a Python engineer with five or more years of experience, building and running production AI agent infrastructure on AWS. The work centres on agent orchestration, secure tool execution and runtime controls behind LLM-powered systems at GR8 Tech, a B2B iGaming software provider. The team values reliable, fault-tolerant services with clear cost controls and strong observability.
What you’ll do
- Design, build and operate production-grade AI agent infrastructure and services on AWS.
- Build agent orchestration, stateful workflows and durable execution, with checkpointing and recovery.
- Build MCP-based integrations and secure tool execution, plus reusable platform components, APIs and SDKs.
- Implement LLM gateways with model routing, fallbacks and cost controls.
- Add observability, tracing and evaluation for agentic workflows, and tune latency, scalability and infrastructure cost.
- Own solutions from architecture through production support, including authentication and authorization for agents and tools.
- Add human-in-the-loop approvals and execution safeguards, and set engineering standards for secure AI systems.
What they’re looking for
- 5+ years of software engineering experience, with strong Python backend skills
- Proven experience building and operating LLM-powered systems in production
- Hands-on work with agent orchestration frameworks such as LangGraph or similar
- Practical experience with LLM APIs, tool or function calling, and agentic workflows
- Solid grasp of distributed systems, asynchronous processing and fault tolerance
- Experience with Pydantic or equivalent for type safety, validation and schemas
- Experience with cloud infrastructure (AWS preferred), Docker and CI/CD
- Understanding of API security, authentication and authorization
- Strong fundamentals in system design, testing, debugging and observability
- Ability to design, build and operate complex components independently
Nice to have
- Production experience with LangGraph and LangChain
- Experience with MCP servers, clients, gateways and tool integration
- Durable workflows, checkpointing and distributed state management
- LLM gateways, model routing, caching and inference optimization
- Agent evaluation and tracing with tools such as MLflow, Langfuse or OpenTelemetry
- Kubernetes (EKS), event-driven architecture and platform engineering
- Agent security, sandboxing and human-in-the-loop workflows
- RAG architectures and vector databases
What’s on offer
- Cafeteria budget covering sports, medical, mental health, home office and language learning
- Paid maternity and paternity leave
- Monthly childcare allowance
- 20+ vacation days, unlimited sick leave and emergency time off
- Remote-first setup with tech support and coworking compensation
- Team events online, offline and offsite
- Internal courses and growth programmes
Skills
Questions about this role
Is this role remote?
Yes. The listing is remote, with a remote-first setup and coworking compensation.
How many years of experience are required?
At least five years of software engineering experience, with strong Python backend skills.
What are the core technical requirements?
Python, LLM APIs and tool calling, agent orchestration such as LangGraph, AWS, Docker and CI/CD, and a background in distributed systems.