About this role
As a Forward Deployed Engineer (FDE) in Applied AI, you are the "Agent Engineer" and the primary driver for our customers' most critical AI initiatives. You take initial conversational prototypes and transform them into production-ready solutions, owning the end-to-end engineering lifecycle, including the transition from "Art of the Possible" to real-world business value and scalable, secure AI systems. This is a high-travel role focused on leading technical delivery for Conversational AI pilots and establishing the first Customer User Journeys (CUJs) for our largest customers at their sites. This role requires a deep understanding of software engineering, Machine Learning Operations, and cloud infrastructure.
Minimum qualifications:
- Bachelor’s degree in Engineering, Computer Science, a related field, or equivalent practical experience.
- 5 years of experience with software development using Python or similar coding languages.
- Experience in data management concepts or technologies and warehousing concepts and technologies (e.g., BigQuery).
- Experience in a data science or analyst role solving business problems using statistical methods, predictive analytics, or Machine Learning.
- Experience in data analysis tools (e.g., SQL, MySQL) and techniques (e.g., Machine Learning, statistical analysis, data mining).
Preferred qualifications:
- Experience implementing multi-agent systems using frameworks (e.g., LangGraph, CrewAI, ADK) and complex patterns (e.g., ReAct, self-reflection, hierarchical delegation).
- Experience tracking LLM-native metrics (e.g., tokens/sec, cost-per-request) and managing state and granular tracing.
- Experience in prompt development, model evaluation, and the creative application of artificial intelligence.
- Experience with BigQuery, Spanner, Apache Spark, Looker, or equivalent cloud data platforms and open table formats.
- Experience building applications on language models over enterprise data and evaluating them for quality, latency, and cost.
- Experience migrating analytics, Spark, or database workloads between platforms with measured cost or performance outcomes.
- Build and ship production data and machine learning workloads with customers, writing, testing, and performance-tuning PySpark, SQL and Python on BigQuery, Managed Spark, Spanner and AlloyDB.
- Build the data foundation for agentic solutions, including lakehouse architectures, metadata and semantic context, and the access controls that let custom agents act on trusted data.
- Train, evaluate and deploy machine learning and agentic components where they improve the customer’s business metric, with evaluation and monitoring in place.
- Refactor and migrate high-cost analytics, Spark and operational database workloads from other platforms onto Google Cloud engines, with measured price-performance results.
- Stand up working proofs with customers’ data, including de-identifying sensitive data (e.g., PCI, PHI).