Merkle is looking to implement cutting-edge artificial intelligence solutions, including agentic AI systems and enterprise-scale LLM deployments, to transform how clients engage with their data and customers. The AI Engineering Lead will be responsible for designing and building production-grade AI solutions that leverage the latest technology, agentic architectures, and cloud-native infrastructure, with a strong focus on natural language interfaces and data democratization through conversational insights.
Requirements
- 5+ years of software engineering experience with at least 2 years focused on AI/ML systems in production environments, preferably including text-to-SQL or conversational analytics implementations
- Deep hands-on experience building LLM-based applications including prompt engineering, RAG implementations, multi-agent systems, and natural language interfaces for data
- Proven expertise in cloud platforms (AWS/Azure/GCP) with specific experience in Databricks (Unity Catalog, Genie) or Snowflake (Cortex, Native Apps) highly preferred
- Strong background in MLOps practices and data engineering including semantic layer design, SQL optimization, and evaluation pipeline implementation
- Experience with modern AI stack including vector databases, orchestration frameworks (LangChain, LlamaIndex), and specialized evaluation tools for conversational AI quality
- Track record of building high-throughput, low-latency systems that handle enterprise scale, including text-to-SQL systems with high accuracy rates
- Production experience with multiple LLM providers and understanding of their trade-offs for various use cases including SQL generation
Responsibilities
- Architect and build enterprise-scale AI systems including agentic workflows, RAG architectures, conversational analytics platforms, and text-to-SQL solutions that are built to scale
- Design and implement semantic layers that enable accurate natural language to SQL translation across complex enterprise data warehouses in Databricks, Snowflake, or AWS platforms
- Lead MLOps/DevOps practices for AI systems including CI/CD pipelines, infrastructure as code, automated testing frameworks, and production monitoring solutions
- Develop robust evaluation frameworks including golden datasets for text-to-SQL accuracy, agent quality metrics, and comprehensive system performance benchmarks
- Design data architectures for AI systems including knowledge base design, vector databases, retrieval optimization, semantic modeling, and real-time data pipelines
- Build conversational insights systems following proven methodologies: requirements gathering, semantic layer implementation, evaluation framework creation, and successful client handoff
- Own the technical roadmap for AI capabilities including evaluation of emerging technologies, proof of concepts for new approaches, and strategic partnerships with cloud providers
Other
- Translate business requirements into scalable, reliable AI systems
- Establish best practices that ensure successful deployments across our client base
- Lead technical client engagements as the engineering SME for complex implementations, providing architectural guidance for both traditional AI and conversational analytics deployments
- Establish engineering standards for prompt engineering, SQL generation quality, model selection, and guardrails implementation that ensure consistent, high-quality AI experiences
- Mentor and develop a team of AI engineers while fostering a culture of technical excellence and continuous learning
