<p><strong></strong></p> <p><strong><span data-contrast="auto">About BEES</span></strong></p> <p><span data-contrast="auto">Join us to build the future of B2B commerce!</span><br><span data-contrast="auto">BEES is AB InBev’s B2B platform. Through our ecosystem, merchants and retailers across 29 countries can stock their businesses quickly, easily, and securely.</span> <br><span data-contrast="auto">At BEES, we dream big, lead with purpose, and develop technology that transforms the way retailers and sellers grow.</span> <span data-ccp-props="{"201341983":0,"335559739":0,"335559740":240}"><br></span><span data-contrast="auto">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!</span> <span data-ccp-props="{"134233117":true,"134233118":true,"201341983":0,"335559739":0,"335559740":240}"> </span></p> <p><strong></strong></p> <p><strong>What you'll do:</strong></p> <ul> <li>Design, develop, and deploy multi-agent AI systems for reasoning, planning, and task execution.</li> <li>Implement RAG (Retrieval-Augmented Generation) pipelines, using orchestration tools and frameworks (LangChain, LangGraph, <em>Azure</em> AI Foundry).</li> <li>Optimize model serving for low-latency, high-throughput inference using frameworks like KServe, Triton Inference Server, or Ray Serve.</li> <li>Build observability and evaluation frameworks to monitor agent reasoning, success rates, and failure cases.</li> <li>Collaborate with ML and data engineers to integrate structured and unstructured data sources into agent workflows.</li> <li>Apply security and alignment techniques (guardrails, prompt injection prevention, red-teaming) to ensure robust behavior.</li> <li>Work in a CI/CD environment (<em>Azure</em> DevOps, GitHub Actions, ArgoCD) for rapid iteration and reliable deployment.</li> <li>Participate in architectural decisions involving distributed systems, GPU usage, caching strategies, and memory management.</li> </ul> <p><strong>What you'll need:</strong></p> <ul> <li>Strong proficiency in <em>Python</em> (for prototyping) and C++/Go (for performance-critical components).</li> <li>Proven experience with LLMs (OpenAI, Anthropic, Llama, Mistral, or similar).</li> <li>Practical experience with agent orchestration frameworks (LangChain, LangGraph, Semantic Kernel).</li> <li>Deep understanding of search and retrieval systems (vector databases like Pinecone, Weaviate, FAISS, Milvus).</li> <li>Knowledge of distributed systems and experience deploying ML models in Kubernetes/AKS/EKS/GKE environments.</li> <li>Familiarity with ONNX Runtime, TensorRT, or DeepSpeed for inference optimization.</li> <li>Experience with public clouds (<em>Azure</em>, AWS, or GCP) and infrastructure as code (Terraform, CloudFormation, or Bicep).</li> <li>Understanding of AI security (prompt injection, data leakage, adversarial testing).</li> </ul> <p><strong>Nice to have:</strong></p> <ul> <li>Experience with multi-agent simulations (AutoGen, CrewAI, OpenAI Swarm).</li> <li>Background in red-teaming and offensive security for AI models.</li> <li>Knowledge of graph databases (Neo4j, ArangoDB) for agent memory and reasoning.</li> <li>Publications, research contributions, or involvement in open-source projects related to LLM or agent frameworks.</li> </ul> <p><strong>What We Offer:</strong></p> <ul> <li>Performance based bonus*</li> <li>Attendance Bonus* </li> <li>Private pension plan</li> <li>Meal Allowance</li> <li>Casual office and dress code</li> <li>Days off*</li> <li>Health, dental, and life insurance</li> <li>Medicines discounts</li> <li>WellHub partnership</li> <li>Childcare subsidies</li> <li>Discounts on Ambev products*</li> <li>Clube Ben partnership</li> <li>Scholarship*</li> <li>School materials assurance</li> <li>Language and training platforms</li> <li>Transport allowance</li> </ul> <p>*Rules applied</p>