About the role
About BEES
Join us to build the future of B2B commerce!
BEES is AB InBev’s B2B platform. Through our ecosystem, merchants and retailers across 29 countries can stock their businesses quickly, easily, and securely.
At BEES, we dream big, lead with purpose, and develop technology that transforms the way retailers and sellers grow.
Every line of code and every partnership is built in service of a single mission: to make commerce better for retailers and sellers around the world. Here, your work is not just important. It makes a difference!
What you'll do
- Design, develop, and deploy multi-agent AI systems for reasoning, planning, and task execution.
- Implement RAG (Retrieval-Augmented Generation) pipelines, using orchestration tools and frameworks (LangChain, LangGraph, Azure AI Foundry).
- Optimize model serving for low-latency, high-throughput inference using frameworks like KServe, Triton Inference Server, or Ray Serve.
- Build observability and evaluation frameworks to monitor agent reasoning, success rates, and failure cases.
- Collaborate with ML and data engineers to integrate structured and unstructured data sources into agent workflows.
- Apply security and alignment techniques (guardrails, prompt injection prevention, red-teaming) to ensure robust behavior.
- Work in a CI/CD environment (Azure DevOps, GitHub Actions, ArgoCD) for rapid iteration and reliable deployment.
- Participate in architectural decisions involving distributed systems, GPU usage, caching strategies, and memory management.
What you'll need
- Strong proficiency in Python (for prototyping) and C++/Go (for performance-critical components).
- Proven experience with LLMs (OpenAI, Anthropic, Llama, Mistral, or similar).
- Practical experience with agent orchestration frameworks (LangChain, LangGraph, Semantic Kernel).
- Deep understanding of search and retrieval systems (vector databases like Pinecone, Weaviate, FAISS, Milvus).
- Knowledge of distributed systems and experience deploying ML models in Kubernetes/AKS/EKS/GKE environments.
- Familiarity with ONNX Runtime, TensorRT, or DeepSpeed for inference optimization.
- Experience with public clouds (Azure, AWS, or GCP) and infrastructure as code (Terraform, CloudFormation, or Bicep).
- Understanding of AI security (prompt injection, data leakage, adversarial testing).
Nice to have
- Experience with multi-agent simulations (AutoGen, CrewAI, OpenAI Swarm).
- Background in red-teaming and offensive security for AI models.
- Knowledge of graph databases (Neo4j, ArangoDB) for agent memory and reasoning.
- Publications, research contributions, or involvement in open-source projects related to LLM or agent frameworks.
What We Offer
- Performance based bonus*
- Attendance Bonus*
- Private pension plan
- Meal Allowance
- Casual office and dress code
- Days off*
- Health, dental, and life insurance
- Medicines discounts
- WellHub partnership
- Childcare subsidies
- Discounts on Ambev products*
- Clube Ben partnership
- Scholarship*
- School materials assurance
- Language and training platforms
- Transport allowance
*Rules applied