AI Engineer - Bees Personalization

<p><strong></strong></p> <p><strong><span data-contrast="auto">About BEES</span></strong><span data-ccp-props="{&quot;201341983&quot;:0,&quot;335559739&quot;:0,&quot;335559740&quot;:240}">&nbsp;</span></p> <p><span data-contrast="auto">Join us to build the future of B2B commerce!</span><span data-ccp-props="{&quot;201341983&quot;:0,&quot;335559739&quot;:0,&quot;335559740&quot;:240}"> <br></span><span data-contrast="auto">BEES is AB InBev’s B2B platform. Through our ecosystem,&nbsp;merchants&nbsp;and retailers across 29 countries can stock their businesses quickly, easily, and securely.</span>&nbsp;<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="{&quot;201341983&quot;:0,&quot;335559739&quot;:0,&quot;335559740&quot;: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&nbsp;just important. It makes a difference!</span><span data-ccp-props="{&quot;201341983&quot;:0,&quot;335559739&quot;:0,&quot;335559740&quot;:240}">&nbsp;</span></p> <p><strong>About the job</strong></p> <p>We are looking for a highly skilled AI Engineer to join our team and lead the design and implementation of complex AI agents capable of reasoning, planning, and collaborating with humans and other systems. This role goes beyond building simple chatbots: you will be responsible for creating multi-agent architectures, integrating advanced LLMs, and ensuring robustness, scalability, and security in production environments.</p> <p>You&nbsp;will&nbsp;work&nbsp;closely&nbsp;with&nbsp;product&nbsp;managers,&nbsp;data&nbsp;engineers,&nbsp;and&nbsp;security&nbsp;specialists&nbsp;to&nbsp;develop&nbsp;agent-based&nbsp;systems&nbsp;that&nbsp;handle&nbsp;real-world&nbsp;complexity&nbsp;at&nbsp;scale.</p> <p><strong>What you'll do:</strong></p> <ul> <li>Design,&nbsp;develop,&nbsp;and&nbsp;deploy&nbsp;multi-agent&nbsp;AI&nbsp;systems&nbsp;for&nbsp;reasoning,&nbsp;planning,&nbsp;and&nbsp;task&nbsp;execution.</li> <li>Implement RAG (Retrieval-Augmented Generation) pipelines, using orchestration tools and frameworks&nbsp;(LangChain,&nbsp;LangGraph,&nbsp;<em>Azure</em>&nbsp;AI&nbsp;Foundry).</li> <li>Optimize model serving for low-latency, high-throughput inference using frameworks like KServe,&nbsp;Triton&nbsp;Inference&nbsp;Server,&nbsp;or&nbsp;Ray&nbsp;Serve.</li> <li>Build&nbsp;observability&nbsp;and&nbsp;evaluation&nbsp;frameworks&nbsp;to&nbsp;monitor&nbsp;agent&nbsp;reasoning,&nbsp;success&nbsp;rates,&nbsp;and&nbsp;failure&nbsp;cases.</li> <li>Collaborate&nbsp;with&nbsp;ML&nbsp;and&nbsp;data&nbsp;engineers&nbsp;to&nbsp;integrate&nbsp;structured&nbsp;and&nbsp;unstructured&nbsp;data&nbsp;sources&nbsp;into&nbsp;agent&nbsp;workflows.</li> <li>Apply security and alignment techniques (guardrails, prompt injection prevention, red-teaming)&nbsp;to&nbsp;ensure&nbsp;robust&nbsp;behavior.</li> <li>Work&nbsp;in&nbsp;a&nbsp;CI/CD&nbsp;environment&nbsp;(<em>Azure</em>&nbsp;DevOps,&nbsp;GitHub&nbsp;Actions,&nbsp;ArgoCD)&nbsp;for&nbsp;rapid&nbsp;iteration&nbsp;and&nbsp;reliable&nbsp;deployment.</li> <li>Participate in architectural decisions involving distributed systems, GPU usage,&nbsp;caching&nbsp;strategies,&nbsp;and&nbsp;memory&nbsp;management.</li> </ul> <p><strong>What you'll need:</strong></p> <ul> <li>Strong&nbsp;proficiency&nbsp;in&nbsp;<em>Python</em>&nbsp;(for&nbsp;prototyping)&nbsp;and&nbsp;C++/Go&nbsp;(for&nbsp;performance-critical&nbsp;components).</li> <li>Proven&nbsp;experience&nbsp;with&nbsp;LLMs&nbsp;(OpenAI,&nbsp;Anthropic,&nbsp;Llama,&nbsp;Mistral,&nbsp;or&nbsp;similar).</li> <li>Practical&nbsp;experience&nbsp;with&nbsp;agent&nbsp;orchestration&nbsp;frameworks&nbsp;(LangChain,&nbsp;LangGraph,&nbsp;Semantic&nbsp;Kernel).</li> <li>Deep understanding of search and retrieval systems&nbsp;(vector&nbsp;databases&nbsp;like&nbsp;Pinecone,&nbsp;Weaviate,&nbsp;FAISS,&nbsp;Milvus).</li> <li>Knowledge of distributed systems and experience deploying&nbsp;ML&nbsp;models&nbsp;in&nbsp;Kubernetes/AKS/EKS/GKE&nbsp;environments.</li> <li>Familiarity&nbsp;with&nbsp;ONNX&nbsp;Runtime,&nbsp;TensorRT,&nbsp;or&nbsp;DeepSpeed&nbsp;for&nbsp;inference&nbsp;optimization.</li> <li>Experience&nbsp;with&nbsp;public&nbsp;clouds&nbsp;(<em>Azure</em>, AWS, or GCP) and infrastructure as code&nbsp;(Terraform,&nbsp;CloudFormation,&nbsp;or&nbsp;Bicep).</li> <li>Understanding&nbsp;of&nbsp;AI&nbsp;security&nbsp;(prompt&nbsp;injection,&nbsp;data&nbsp;leakage,&nbsp;adversarial&nbsp;testing).</li> </ul> <p><strong>Nice&nbsp;to&nbsp;have:</strong></p> <ul> <li>Experience&nbsp;with&nbsp;multi-agent&nbsp;simulations&nbsp;(AutoGen,&nbsp;CrewAI,&nbsp;OpenAI&nbsp;Swarm).</li> <li>Background&nbsp;in&nbsp;red-teaming&nbsp;and&nbsp;offensive&nbsp;security&nbsp;for&nbsp;AI&nbsp;models.</li> <li>Knowledge&nbsp;of&nbsp;graph&nbsp;databases&nbsp;(Neo4j,&nbsp;ArangoDB)&nbsp;for&nbsp;agent&nbsp;memory&nbsp;and&nbsp;reasoning.</li> <li>Publications,&nbsp;research&nbsp;contributions,&nbsp;or&nbsp;involvement&nbsp;in&nbsp;open-source&nbsp;projects&nbsp;related&nbsp;to&nbsp;LLM&nbsp;or&nbsp;agent&nbsp;frameworks.</li> </ul> <p>&nbsp;</p> <p><strong>What We Offer:</strong></p> <ul> <li>Performance based bonus*</li> <li>Attendance Bonus*&nbsp;</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> <p><strong></strong></p> <p>&nbsp;</p> <p>&nbsp;</p>