Embark on a journey as an Application Support Engineer, where you'll act as a software detective. Your mission is to provide a dynamic service, identifying and resolving complex issues within critical business systems. This role demands a keen analytical mind and a proactive approach to ensuring system stability and performance.

We are seeking a skilled Generative AI Engineer with extensive experience in Databricks and AWS. You will be instrumental in designing, building, and scaling LLM-powered, agentic AI solutions tailored for enterprise-grade applications. The focus is on creating intelligent agents, robust RAG pipelines, and AI-driven data products that are production-ready, scalable, secure, and cost-effective.

Key responsibilities include designing and developing GenAI and Agentic AI solutions leveraging LLMs for diverse enterprise use cases. You will build RAG pipelines using structured and unstructured data, and implement AI agents and workflows utilizing AWS Agent Core/Bedrock and orchestration frameworks. Developing GenAI applications on Databricks using notebooks, jobs, and scalable compute, along with integrating these solutions with data lakes, lakehouse, and enterprise systems, are core functions.

Further duties involve optimizing solutions for latency, accuracy, cost, and scalability, and implementing advanced techniques like prompt engineering, prompt chaining, and guardrails. You will collaborate closely with data engineers, architects, and business stakeholders to translate requirements into effective AI-driven solutions and contribute to AI governance, observability, and responsible AI practices. Supporting the deployment, monitoring, and continuous improvement of GenAI systems in production environments is also crucial.

Essential technical skills encompass GenAI/LLM expertise with hands-on experience in models like Claude, OpenAI, and Llama, coupled with a strong understanding of RAG architectures, embeddings, and vector search. Experience in building agentic workflows (planning, tool use, reasoning loops) and applying prompt engineering techniques is vital.

Proficiency in Databricks, including Databricks Lakehouse, PySpark, SQL, Delta Lake, and Databricks workflows/jobs, is required. Experience with MLflow for experimentation and model tracking is expected, with Unity Catalog being a preferred asset. On the AWS front, experience with AWS Bedrock, AWS Agent Core or agent orchestration patterns, Lambda, API Gateway, S3, and IAM best practices for AI workloads is necessary.

Strong programming skills in Python (advanced) and SQL, along with experience in APIs and microservices integration, are fundamental. Good-to-have skills include familiarity with frameworks like LangChain/LangGraph/DSPy, vector databases (OpenSearch, FAISS, Pinecone), LLMOps/MLOps, CI/CD for AI applications, and knowledge of AI governance, compliance, and security. Prior experience in client-facing or consulting roles is beneficial.