Description & Requirements
Introduction: A Career at HARMAN Automotive
We're a global, multi-disciplinary team that's putting the innovative power of technology to work and transforming tomorrow. At HARMAN Automotive, we give you the keys to fast-track your career.
Engineer audio systems and integrated technology platforms that augment the driving experience
Combine ingenuity, in-depth research, and a spirit of collaboration with design and engineering excellence
Advance in-vehicle infotainment, safety, efficiency, and enjoyment
About the Role
Drive hands-on delivery of AI and Generative AI solutions that streamline supply chain workflows and deliver measurable business value through hours saved, cycle-time reduction, improved decision quality, risk mitigation, and the breadth of users served. You will architect, develop, and maintain production-grade systems encompassing RAG pipelines, agentic tools, model routing, vector search, evaluation and guardrails, and observability, all tightly integrated with internal platforms, enterprise datasets, and supply chain systems. This is primarily a hands-on GenAI and software engineering role, with supply chain expertise providing the domain context for solution design and delivery.
What You Will Do
Automate high-impact supply chain workflows for internal stakeholders, prioritizing initiatives with the greatest time savings, business impact, and user reach.
Deliver production-ready copilots and applications for knowledge search, document summarization, intelligent recommendations, conversational analytics, exception management, and end-to-end workflow automation.
Apply GenAI and software engineering to supply chain use cases across procurement; supplier collaboration and management; risk management; quality; costing; engineering; materials and warehouse management; finished-goods and component-level planning; and ESG.
Architect and develop scalable, high-performance data and AI systems that support RAG, agentic workflows, secure tool use, and model orchestration.
Own the complete solution lifecycle, from problem definition and rapid prototyping through rigorous evaluation, production deployment, ongoing monitoring, and continuous improvement.
Design and implement RAG pipelines over heterogeneous and often messy enterprise and supply chain data, including contracts, purchase orders, supplier documents, bills of material, requirements, quality records, audit artifacts, planning data, business rules, and unstructured content. Select embedding strategies, chunking approaches, vector search configurations, rerankers, metadata or knowledge-graph enrichment techniques, and routing policies to maximize retrieval quality.
Develop agentic workflows leveraging LangChain, LlamaIndex, Model Context Protocol (MCP), and agent-to-agent (A2A) protocols; build secure tools that allow agents to retrieve data and execute approved actions in enterprise systems.
Integrate AI solutions with enterprise applications and data platforms through APIs, events, batch pipelines, and governed access patterns; design integrations that are resilient, observable, and maintainable.
Evaluate when to use platform-native embedded AI capabilities versus custom-built GenAI components, and design modular solutions that can evolve with the enterprise tool landscape.
Translate subject-matter-expert knowledge into robust prompts, tools, workflow logic, and validation rules; evaluate trade-offs among prompt engineering, retrieval augmentation, fine-tuning, and deterministic software.
Work hands-on with large language models, vector databases such as Pinecone and FAISS, and agent memory systems.
Establish operational excellence through rigorous SLAs; safety and guardrail mechanisms; prompt and version management; transparent evaluation; latency and throughput optimization; cost controls; load balancing; fallback or model-routing strategies; and human review for process-critical decisions.
Establish observability using tools such as Datadog, Grafana, and LangFuse, along with model and data governance, access controls, auditability, and operational support appropriate for internal enterprise environments.
Build and maintain data products, lakes, and warehouses using platforms such as Snowflake, Delta Lake, BigQuery, and Microsoft Fabric to support supply chain AI use cases.
Build internal copilots and customer-facing features using React, Node.js, and Python with REST or GraphQL backends; containerize applications with Docker, orchestrate with Kubernetes, automate CI/CD pipelines, and manage infrastructure as code using tools such as Terraform.
Collaborate closely with supply chain subject-matter experts, requirements, testing, validation, cybersecurity, data, platform, and enterprise application teams; communicate proactively and iterate rapidly in a fast-paced environment.
What You Need To Be Successful
8+ years of experience building production software, ideally including ML systems and hands-on work with LLMs and Generative AI; demonstrated technical leadership while remaining deeply hands-on.
Programming: Python (FastAPI, NumPy, Pandas, scikit-learn, Pydantic, Jinja2) and Node.js; strong proficiency with APIs and distributed systems.
LLMs and Frameworks: Hands-on experience with at least one major deep learning or LLM stack, such as PyTorch/Transformers or TensorFlow/Keras, and orchestration frameworks such as LangChain or LlamaIndex.
Model Providers: Working familiarity connecting to inference providers and model ecosystems such as AWS Bedrock, OpenAI, Anthropic, Meta/Llama, and Mistral.
Data and Storage: SQL and NoSQL databases... For full info follow application link.
HARMAN is an Equal Opportunity /Affirmative Action employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability or Protected Veterans status.
