Senior Forward-Deployed AI Engineer (Snowflake) at Abacus Insights in United States

Job description

• The Sr. Forward-Deployed AI Engineer is a senior individual contributor responsible for designing and building the AI and GenAI/agentic systems that power our platform on Snowflake, and for carrying that work directly into client environments. Hands-on Snowflake expertise is essential to this role. Databricks experience is a plus but not required.
• This is a forward-deployed role: the person in this seat spends a meaningful share of their time working inside client environments, not just building systems that clients eventually use. Candidates must bring prior, evidenced experience doing this kind of work already.
• The role's focus will shift over time. Initially, the work is centered on configuring the Snowflake semantic layer and delivering metrics and reporting off of it for clients. As that foundation matures, the role expands into agentic AI work, which depends directly on the semantic layer already being correctly modeled and configured.
• On client engagements, this person is the senior-most AI technical voice, trusted to work through ambiguous problems and help shape the technical vision and roadmap for AI components. This is technical leadership, not engagement ownership or people management; someone else owns the engagement and its reporting, and this role does not have direct reports.
• AI/ML architecture and model strategy on Snowflake
• GenAI and agentic systems design
• Direct, hands-on client engagement and implementation
• Unlike a purely internal engineering role, this position regularly puts you in front of clients: scoping their needs, implementing solutions in their environment, and troubleshooting alongside them. Candidates should bring demonstrated experience doing this kind of work already, not only an interest in doing it.

Responsibilities

• Semantic Layer & Metrics Reporting (initial focus)
• Design, configure, and maintain the Snowflake semantic layer (e.g. Cortex Analyst semantic views), modeling business logic and metrics definitions accurately against client requirements
• Build and deliver metrics and reporting for clients off of the configured semantic layer
• Work directly with client stakeholders to define metrics requirements, validate outputs against business logic, and resolve discrepancies
• Write efficient, production-grade SQL and Python to support semantic layer configuration, metrics pipelines, and reporting delivery
• GenAI & Agentic Systems (as the role evolves)
• Design and implement retrieval-augmented generation (RAG) systems, agentic workflows, and MCP-based tooling that draw on the semantic layer as their source of truth
• Build and maintain evaluation harnesses to test and monitor AI/agent quality and performance
• Apply sound judgment on model selection, prompting strategy, and system design tradeoffs
• Own technical architecture and model strategy decisions for AI systems built on the Snowflake platform
• Client-Facing / Forward Deployed Engineering
• Serve as the senior-most AI technical voice on client engagements, helping shape technical direction and roadmap for AI components, without owning the engagement or its reporting
• Work directly with client stakeholders to scope AI/ML use cases, translate business requirements into technical solutions, and set realistic expectations on scope and timeline
• Implement and configure solutions within client environments, adapting the platform to client-specific data and constraints
• Serve as the technical point of contact for clients during implementation, including troubleshooting issues live with client teams
• Manage client relationships and expectations with the same rigor applied to the technical work itself
• Cross-Functional Collaboration
• Partner with product, data science, and operations teams to move AI/ML work from prototype to production
• Communicate technical tradeoffs clearly to both technical and non-technical audiences, internal and client-facing
• Contribute to team best practices for AI engineering and client implementation work

Requirements

• 8+ years of software/AI engineering experience, including hands-on design of AI/ML systems
• Deep, hands-on experience with Snowflake, including Snowpark, Snowflake Cortex, and Snowflake ML
• Hands-on experience building and maintaining semantic layers on Snowflake (e.g. Cortex Analyst semantic views), including modeling business logic and metrics for AI/agent consumption
• Experience delivering metrics and reporting off of a semantic layer for clients, including validating outputs against business logic
• Demonstrated experience designing and building GenAI/agentic systems: RAG, MCP-based tooling, agent orchestration patterns, and evaluation harnesses
• A proven track record working directly with external clients or customers in an implementation, forward-deployed, or professional-services capacity, with specific engagements you personally owned, not only internal engineering experience
• Demonstrated ability to operate as the senior technical voice on ambiguous problems, with sound judgment on AI technical direction, without needing close direction
• Strong Python engineering skills, including API design and delivery of production AI/ML pipelines
• Strong communication skills, with demonstrated ability to translate technical tradeoffs for non-technical, client-facing audiences
• Comfort operating with a degree of ambiguity typical of client environments, and sound judgment on when to escalate versus resolve independently
• Hands-on experience with Databricks, including Unity Catalog, Delta Lake, and MLflow
• Healthcare payer or provider claims data experience
• Experience with classical ML and with model fine-tuning
• Relevant certifications (e.g. SnowPro)

Skills

Required

• SQL
• AI/ML architecture and model strategy

Preferred

• Healthcare payer or provider claims data
• Classical ML and model fine-tuning
• Relevant certifications (e.g. SnowPro)