Description & Requirements About the Role Drive hands-on delivery of AI and Generative AI solutions that streamline workflows and deliver measurable business value-measured by hours saved and the breadth of users served. You will architect, develop, and maintain production-gra de systems encompassing RAG pipelines, agentic tools, model routing, vector search, evaluation, and guardrails, and o bservability-a ll tightly integrated with internal platforms and enterprise datasets.
What You Will Do • Automate high-impact workflows for internal stakeholders, prioritizing initiatives with the greatest time savings and broadest user reach.
• Deliver production-rea dy copilots and customer-facin g applications for knowledge search, document summarization, intelligent recommendation s, conversational analytics, and end-to-end workflow automation.
• Establish operational excellence through rigorous SLAs, latency and throughput optimization, robust safety and guardrail mechanisms, transparent evaluation frameworks, and cost-efficient inference strategies.
• Architect and develop scalable, high-performan ce data and AI systems that support GenAI use cases including RAG, agentic workflows, and model orchestration.
• Own the complete solution lifecycle: problem definition → rapid prototyping → rigorous evaluation → production deployment → ongoing monitoring.
• Implement guardrails (content policies, safety filters), prompt and version management, latency and throughput tuning, cost controls, load balancing, and fallback or model-routing strategies.
• Design and implement RAG pipelines over heterogeneous and often messy datasets-inclu ding requirements documents, lessons learned, business rules, and unstructured content.
• Select appropriate embedding strategies, chunking approaches, vector search c onfigurations, rerankers, and routing policies to maximize retrieval quality.
• Develop agentic workflows leveraging LangChain, LlamaIndex, MCP, and agent-to-agent (A2A) protocols; build tooling for agentic coding use cases.
• Translate su bject-matter-e xpert knowledge into robust, maintainable prompts; evaluate trade-offs between fine-tuning and prompt engineering.
• Work hands-on with large language models, vector databases (Pinecone, FAISS), and agent memory systems.
• Containerize applications with Docker, orchestrate with Kubernetes, and automate CI/CD pipelines; manage infrastructure as code (e.g. Terraform).
• Establish observability (Datadog, Grafana, LangFuse), evaluation frameworks, and model/data governance and access controls appropriate for internal enterprise environments.
• Bring experience building and maintaining data lakes and warehouses (Snowflake, Delta Lake, BigQuery, MS Fabric).
• Build internal copilots and customer-facin g features using React, Node.js, and Python with REST or GraphQL backends.
• Collaborate closely with requirements, testing, validation, and platform teams; thrive in a fast-paced environment with clear, proactive communication and rapid iteration.
What You Need To Be Successful - 8+ years of experience building production software
• Programming: Python (FastAPI, NumPy, Pandas, scikit-learn, Pydantic, Jinja2) and Node.js; strong proficiency with APIs and distributed systems.
• Model Providers: Working familiarity with connecting to inference providers e.g. AWS Bedrock, along with OpenAI, Anthropic, Meta/Llama, and Mistral model ecosystems.
• Data & Storage: SQL and NoSQL databases (PostgreSQL, DynamoDB), Elasticsearch for search and analytics, and vector databases (Pinecone, Weaviate, FAISS, Milvus, pgvector).
• Cloud & Infrastructure: AWS (S3, EC2, Lambda, CloudWatch, Fargate, EKS/ECS), Azure, GCP, Databricks, Docker, Kubernetes, Terraform, CI/CD, Airflow, and Kafka.
• Operational Excellence: Load balancing, monitoring, and alerting (Datadog, Grafana, LangFuse), debugging production issues, and cost/performance optimization.
• Soft Skills: Strong communication abilities, product-oriented thinking, and the capacity to learn and adapt quickly in a dynamic environment.
• Education: BS, MS, or PhD in Computer Science, Electrical Engineering, Mathematics, or equivalent professional experience
What Is Nice To Have- Experience building ML Systems
- LLMs & Frameworks: Hands-on experience with at least one major deep learning or LLM stack (e.g., PyTorch/Transformers, TensorFlow/Keras) and orchestration frameworks such as LangChain or LlamaIndex.
What Makes You Eligible * Be willing to work in an office located in Novi, MI (hybrid)
What We Offer * Access to employee discounts on world-class products (JBL, HARMAN Kardon, AKG, and more)
* Extensive training opportunities through our own HARMAN University
* Competitive wellness benefits
* Tuition reimbursement
* "Be Brilliant" employee recognition and rewards program
* An inclusive and diverse work environment that fosters and encourages professional and personal development
#Hybrid
Pay Transparency
$ 125,250 - $ 183,700
Dependent on the position offered, other forms of compensation are also available, such as bonuses or commission.
Pay is based on a wide range of factors, including, without limitation, skill set, experience, training, location, and business need. While the above range is a reasonable estimate of the wage range for this position, please note the disclosed range estimate has not been adjusted for the applicable geographical differential associated with the location where the position may be filled.
BenefitsHARMAN is interested in the health and wellbeing of you and your family and offers a range of benefits designed to support your needs for holistic wellbeing. Benefits and perks may vary depending on the nature of your employment with HARMAN, and may include paid vacation and holidays, paid sick leave, volunteer leave, and paid bonding and care giver leave. Employees may also be eligible to participate in comprehensive medical, dental, and vision plans, fertility support and adoption assistance, Health Savings and Flexible Spending Accounts, retirement savings plan with employer match, short and long term disability coverage, life insurance, and more.
