Runs the team day to day
In-house, owns the opening
Joined the team recently
From your own Gmail and LinkedIn.
How this role compares
One of 46 open AI Engineer roles we are tracking today.
Posted november 2026, with 3 of the others posted since and 42 still open from before.
Counted across the roles Frontrunner has open right now.
About the role
This is a remote AI engineering role open to candidates anywhere in the world, working on multi-agent AI systems for reasoning, planning and task execution. The work sits inside the Growth Group, which covers B2B commerce, direct-to-consumer, sales and marketing for a global brewer. You will build retrieval-augmented generation pipelines, serve models at low latency, and build evaluation tooling for agent behaviour. The team expects strong Python and C++ or Go skills, plus experience with LLM frameworks and cloud infrastructure.
What youβll do
- Design, build and deploy multi-agent AI systems for reasoning, planning and task execution.
- Implement retrieval-augmented generation pipelines using orchestration frameworks such as LangChain, LangGraph and Azure AI Foundry.
- Optimise model serving for low-latency, high-throughput inference with KServe, Triton Inference Server or Ray Serve.
- Build observability and evaluation tooling that tracks agent reasoning, success rates and failure cases.
- Work with ML and data engineers to bring structured and unstructured data into agent workflows.
- Apply guardrails, prompt injection defences and red-teaming to keep agent behaviour robust.
- Ship changes through CI/CD pipelines on Azure DevOps, GitHub Actions or ArgoCD.
- Take part in architecture decisions covering distributed systems, GPU use, caching and memory management.
What theyβre looking for
- Strong Python for prototyping, and C++ or Go for performance-critical components.
- Proven experience working with large language models from providers such as OpenAI, Anthropic, Meta Llama or Mistral.
- Practical experience with agent orchestration frameworks such as LangChain, LangGraph or Semantic Kernel.
- Deep understanding of search and retrieval, including vector databases such as Pinecone, Weaviate, FAISS or Milvus.
- Knowledge of distributed systems and experience deploying ML models on Kubernetes, AKS, EKS or GKE.
- Familiarity with ONNX Runtime, TensorRT or DeepSpeed for inference optimisation.
- Experience with a public cloud (Azure, AWS or GCP) and infrastructure as code such as Terraform, CloudFormation or Bicep.
- Understanding of AI security issues including prompt injection, data leakage and adversarial testing.
Nice to have
- Experience with multi-agent simulation frameworks such as AutoGen, CrewAI or OpenAI Swarm.
- Background in red-teaming or offensive security for AI models.
- Knowledge of graph databases such as Neo4j or ArangoDB for agent memory and reasoning.
- Publications, research or open-source contributions related to LLM or agent frameworks.
Whatβs on offer
- Performance-based bonus and attendance bonus, subject to rules.
- Private pension plan, health, dental and life insurance, and medicine discounts.
- Meal and transport allowances, and childcare subsidies.
- Days off, scholarship and school materials assurance, subject to rules.
- Discounts on company products, a WellHub partnership and a Clube Ben partnership.
- Language and training platforms, and a casual office and dress code.
Skills
Questions about this role
Is this AI engineer role remote?
Yes. The posting lists the role as remote with a global location.
What skills do I need for this role?
Strong Python, experience with LLMs and agent frameworks such as LangChain or LangGraph, vector databases, Kubernetes and a public cloud are asked for.
Do I need a degree?
The posting does not state a degree requirement.