Source description
About the role
As a part of the global, multi-disciplinary team at HARMAN Automotive, you will have the opportunity to engineer audio systems and integrated technology platforms that enhance the driving experience. Your role will involve combining ingenuity, in-depth research, and collaboration to achieve design and engineering excellence. By advancing in-vehicle infotainment, safety, efficiency, and enjoyment, you will contribute to transforming tomorrow in the automotive industry. Key Responsibilities: - Fine-tune, supervise, or optimize models for domain-specific tasks - Build "function calling" capabilities for real-time actions - Develop agentic AI systems using frameworks such as LangChain, AutoGen, Semantic Kernel, Haystack, or LlamaIndex - Create multi-agent architectures for planning, reasoning, tool use, memory, and feedback loops - Implement autonomous workflows for analytics, operations, customer support, and productivity automation - Develop LLM-powered features including Natural language querying, Summarization & explanation engines, Scenario simulation & calculators, Insight generation and anomaly detection, and Conversational interfaces - Build enterprise-grade Retrieval-Augmented Generation (RAG) pipelines for scalable document, metric, and knowledge retrieval - Enable agents to interact with Databases, Power BI / Anaplan / ERP / CRM, REST APIs, Python tools & calculators, and Business workflows - Deploy AI systems using Azure ML, AWS Sagemaker, Vertex AI, or on-prem platforms - Collaborate with product, analytics, and engineering teams to design AI use cases - Create high-level and low-level architecture diagrams ensuring scalability, robustness, security, and governance Qualifications Required: - 4-6 years of experience - Strong understanding of Generative AI & LLMs, including GPT, Llama, Mistral, Claude, Gemini - Hands-on experience with Agentic AI technologies like LangChain Agents, AutoGen / Autogen Studio, Semantic Kernel Functions & Planners, and Multi-Agent Orchestration - Proficiency in RAG Engineering, Vector databases (FAISS, Pinecone, Milvus, Azure AI Search), Chunking strategies, and prompt routing & retrieval chains - Programming skills in Python, knowledge of TypeScript/JavaScript, and familiarity with API development - Cloud & Deployment experience with Azure AI Studio / AWS Bedrock / GCP Vertex AI, Docker, Kubernetes, and DevOps & MLOps practices - Data & Analytics proficiency in SQL, data modeling, and working knowledge of APIs from systems like Power BI, Dataverse, Anaplan, SAP, and basic ML knowledge At HARMAN, you will benefit from a flexible work environment, employee discounts, extensive training opportunities, competitive wellness benefits, tuition reimbursement, and a supportive and inclusive work culture that encourages professional and personal development. Please note that HARMAN is committed to equal opportunity employment and strives to build a diverse workforce representative of global marketplaces and communities. If you are ready to innovate and make a lasting impact, consider joining the HARMAN talent community today. As a part of the global, multi-disciplinary team at HARMAN Automotive, you will have the opportunity to engineer audio systems and integrated technology platforms that enhance the driving experience. Your role will involve combining ingenuity, in-depth research, and collaboration to achieve design and engineering excellence. By advancing in-vehicle infotainment, safety, efficiency, and enjoyment, you will contribute to transforming tomorrow in the automotive industry. Key Responsibilities: - Fine-tune, supervise, or optimize models for domain-specific tasks - Build "function calling" capabilities for real-time actions - Develop agentic AI systems using frameworks such as LangChain, AutoGen, Semantic Kernel, Haystack, or LlamaIndex - Create multi-agent architectures for planning, reasoning, tool use, memory, and feedback loops - Implement autonomous workflows for analytics, operations, customer support, and productivity automation - Develop LLM-powered features including Natural language querying, Summarization & explanation engines, Scenario simulation & calculators, Insight generation and anomaly detection, and Conversational interfaces - Build enterprise-grade Retrieval-Augmented Generation (RAG) pipelines for scalable document, metric, and knowledge retrieval - Enable agents to interact with Databases, Power BI / Anaplan / ERP / CRM, REST APIs, Python tools & calculators, and Business workflows - Deploy AI systems using Azure ML, AWS Sagemaker, Vertex AI, or on-prem platforms - Collaborate with product, analytics, and engineering teams to design AI use cases - Create high-level and low-level architecture diagrams ensuring scalability, robustness, security, and governance Qualifications Required: - 4-6 years of experience - Strong understanding of Generative AI & LLMs, including GPT, Llama, Mistral, Claude, Gemini - Hands-on experienc
More at HARMAN