Senior GenAl Engineer

What were looking for Senior GenAl Engineer (Only for people located in Latinamerica). Our client leads the way in AI innovation, leveraging cutting-edge technology to transform legacy systems into modern, efficient, and scalable solutions. They work with enterprise clients to future-proof their applications, helping them meet the demands of today's dynamic digital environment. The team excels at solving complex challenges and delivering AI-powered solutions. They foster a culture of creativity, collaboration, and continuous learning. We are seeking a highly skilled Senior GenAl Engineer (Multi-Agent Systems) to play a key role in advancing our Al-driven platform and client solutions. The ideal candidate has 4+ years of hands-on Machine Learning (ML) experience beyond academia, thrives in fast-paced environments, and enjoys solving complex technical challenges. A strong foundation in cloud-based ML solutions, Al model deployment, and optimization techniques is essential. Those with a passion for staying at the forefront of Al advancements and delivering high impact solutions will excel in this role. Key Responsibilities: Architect and scale multi-agent orchestration frameworks (e.g., LangGraph, AutoGen, Llamalndex, CrewAl)Implement agent-to-agent communication, memory and state management Build evaluation and feedback loops (e.g., latency, success-rate, hallucination control, cost)Integrate agents with external APIs, data systems and event streams Ensure scalability, observability and MLOps for agent workflowsContribute to building and enhancing our Mechanized Al platform and mAln Modernize product suiteServe as ML SME on client projects, as neededDesign ML systemsResearch and implement appropriate ML algorithms and toolsSelect appropriate datasets and data representation methodsRun ML tests and experimentsExtend existing ML libraries and frameworksStay current with emerging technologies and ML best practices to continuously improve our methodologies and tools Experience and knowledge 5+ years of professional software (Al preferred) engineering2+ years building production LLM or multi-agent systemsPractical proficiency with graph databases (e.g., TigerGraph, Neo4j) and graph-based retrieval (e.g., GraphRAG), plus experience with vector databases like Opensearch, CosmosDB, or PineconeDeep experience with one or more: LangGraph, AutoGen 0.4, LlamalndexAgentWorkflow, ag2, strands agents, etcRetrieval for agents: Opensearch plus TigerGraph and GraphRAG patterns for global reasoningObservability: Langfuse or Phoenix with OpenTelemetry; track quality, cost, and latencyServing: Deploy and scale agentic workloads via AWS Fargate, Step Functions, and Lambdas (or equivalent services on other clouds), ensuring p95 latency targetsSafety by design aligned to OWASP LLM Top 10; implement policy-compliant tool scopes and output validation.Interoperability: Model Context Protocol (MCP) for tool and data access, with bonus for LangGraph MCP adaptersExperience with cloud environments (e.g., AWS, Azure, GCP): ECS, Step Functions, Lambda and equivalents on other clouds.Experience developing, deploying, and managing/monitoring non-open source LLMsKnowledge of containerization technologies (e.g., Docker, Kubernetes) and microservices architectureExpertise in Object-Oriented Programming (OOP) principles and unit test-driven development methodologiesRetrieval-augmented generation (RAG) optimizationAdvanced experience in NLP techniques and applicationsStrong proficiency in Python programmingFamiliarity with prompt engineering approaches and best practicesKnowledge of data structures, data modeling, and software architectureBachelor's degree in computer science, software engineering or related fieldStrong analytical and problem-solving skills, with ability to propose innovative solutions and troubleshoot issuesAbility to work independently and as part of a collaborative team in a fast-paced environmentEnglish B2Only for people located in Latinamerica Preferred Qualifications: Agent developmentData privacyFine tuning LLMsLM architecture and techniques for performanceLLMOpsMLevaluationModel decay and data drift detection and handlinglac: Pulumi, Terraform, and/or Cloud SDKsSecurityVector databases Compensation & Benefits Participation in innovative, high-impact regional projects.People-centric culture with autonomy and continuous learning.Work 100% RemoteWork from anywhereWe pay in US dollars.You can enjoy all the holidays in your country.10 days of PTO paymentsCompensation & Benefits Participation in innovative, high-impact regional projects.People-centric culture with autonomy and continuous learning.Work 100% RemoteWork from anywhereWe pay in US dollars.40 USD BYOD.You can enjoy all the holidays in your country.10 days of PTO payments