Leads the team this role joins
In-house, owns the opening
Put the opening up
From your own Gmail and LinkedIn.
How this role compares
One of 46 open AI Engineer roles we are tracking today.
Counted across the roles Frontrunner has open right now.
About the role
This is a remote contract AI engineer role building multi-agent AI systems and retrieval-augmented generation pipelines. It suits engineers who can move LLM agents from prototype to low-latency production serving, working in Python and in C++ or Go for performance-critical parts. The role sits within the AB InBev Growth Group, which brings together business-to-business, direct-to-consumer, sales and distribution, and marketing teams.
What you’ll do
- Design, build and deploy multi-agent AI systems for reasoning, planning and task execution.
- Implement retrieval-augmented generation pipelines with LangChain, LangGraph and Azure AI Foundry.
- Optimize model serving for low-latency, high-throughput inference with KServe, Triton Inference Server or Ray Serve.
- Build observability and evaluation frameworks that track agent reasoning, success rates and failure cases.
- Bring structured and unstructured data into agent workflows with ML and data engineers.
- Apply guardrails, prompt injection prevention and red-teaming to keep agent behavior robust.
- Ship through CI/CD pipelines on Azure DevOps, GitHub Actions and ArgoCD.
- Take part in architecture decisions on distributed systems, GPU usage, caching and memory management.
What they’re looking for
- Strong Python for prototyping, and C++ or Go for performance-critical components.
- Proven experience with LLMs such as OpenAI, Anthropic, Llama, Mistral or similar.
- Practical use of agent orchestration frameworks such as LangChain, LangGraph or Semantic Kernel.
- Deep understanding of search and retrieval systems using vector databases such as Pinecone, Weaviate, FAISS or Milvus.
- Knowledge of distributed systems and experience deploying ML on Kubernetes, AKS, EKS or GKE.
- Familiarity with ONNX Runtime, TensorRT or DeepSpeed for inference optimization.
- Experience with Azure, AWS or GCP and infrastructure as code using Terraform, CloudFormation or Bicep.
- Understanding of AI security, including prompt injection, data leakage and adversarial testing.
Nice to have
- Multi-agent simulation experience with 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 work on LLM or agent frameworks.
What’s on offer
- Fully remote working.
- Engagement listed as a contract role.
Skills
Questions about this role
Is this role remote?
Yes, it is listed as remote.
Is it a contract position?
Yes, the engagement is listed as a contract.
Which languages does the role use?
Python for prototyping, plus C++ or Go for performance-critical components.
Which orchestration tools are named?
LangChain, LangGraph, Semantic Kernel and Azure AI Foundry are named.