Agentic framework Engineer

HARMAN’s engineers and designers are creative, purposeful and agile. As part of this team, you’ll combine your technical expertise with innovative ideas to help drive cutting-edge solutions in the car, enterprise and connected ecosystem. Every day, you will push the boundaries of creative design, and HARMAN is committed to providing you with the opportunities, innovative technologies and resources to build a successful career.

A Career at HARMAN

As a technology leader that is rapidly on the move, HARMAN is filled with people who are focused on making life better. Innovation, inclusivity and teamwork are a part of our DNA. When you add that to the challenges we take on and solve together, you’ll discover that at HARMAN you can grow, make a difference and be proud of the work you do everyday.

Introduction: A Career at HARMAN Digital Transformation Solutions (DTS)

We’re a global, multi-disciplinary team that’s putting the innovative power of technology to work and transforming tomorrow. At HARMAN DTS, you solve challenges by creating innovative solutions.

• Combine the physical and digital, making technology a more dynamic force to solve challenges and serve humanity’s needs
• Work at the convergence of cross channel UX, cloud, insightful data, IoT and mobility
• Empower companies to create new digital business models, enter new markets, and improve customer experiences

About the role

We're looking for a forward-thinking Agentic Process Automation (Agentic AI Engineer) to lead the design and development of AI-native workflows. You'll develop AI Agents that operate across dynamic contexts—learning, deciding, and acting on behalf of users and businesses.

What You Will Do

• Architect and develop autonomous AI agents using cutting-edge agentic frameworks (e.g., Google ADK, LangGraph, AutoGen, CrewAI, OpenAI Agents SDK, etc.)
• Build multi-agent workflows that coordinate perception, reasoning, and action across tools, APIs, and knowledge bases
• Integrate GenAI pipelines using modern tooling such as LangChain, DSPy, MemGPT, LangFuse, LiteLLM, etc.
• Implement scalable RAG, MCP, and A2A systems with support for context-aware decision-making
• Optimize embedding strategies and retrieval performance using vector databases like PgVector, Pinecone, FAISS, Weaviate etc.
• Design intuitive UIs with Human-in-the-loop feedback and robust APIs to facilitate human-agent collaboration
• Establish evaluation and observability pipelines using LLM eval frameworks and feedback loops
• Collaborate across product, design, and research teams to drive continuous innovation

What You Need

• Proficiency in Python and strong grasp of modern Gen AI & ML development workflows
• Hands-on experience with agentic AI frameworks (Google ADK, LangGraph, AutoGen, CrewAI, OpenAI Agents SDK, Pydantic AI etc.)
• Solid understanding of prompt engineering, tool use, agent memory, and action planning
• Experience with Gen AI libraries like LangChian, DSPy, LiteLLM, LangFuse, Mem0 etc.
• Practical knowledge of vector/relational/NoSQL data stores
• Familiarity with fine-tuning, quantization, or deployment of LLMs (a plus)
• Web development experience (Next.js, React, or similar) is a bonus
• Ability to learn rapidly, contribute autonomously, and communicate ideas clearly

HARMAN is proud to be an Equal Opportunity / Affirmative Action employer. All qualified applicants will receive consideration for employment without regard to race, religion, color, national origin, gender (including pregnancy, childbirth, or related medical conditions), sexual orientation, gender identity, gender expression, age, status as a protected veteran, status as an individual with a disability, or other applicable legally protected characteristics.