Design and implement scalable AI architectures, including: LLM-powered applications, Retrieval-Augmented Generation (RAG) systems, agentic / multi-step workflows, vector search and retrieval services, model serving and inference layers.
Establish reusable platform services, APIs, and design patterns to accelerate delivery across multiple teams.
Build and operationalize AI delivery pipelines: CI/CD for models, prompts, and workflows, prompt versioning and lifecycle management, evaluation and testing frameworks, model and artifact registries.
Implement monitoring for response quality and hallucination control, latency, throughput, and system reliability, cost observability and optimization.
Design AI systems with strong controls for data security and privacy auditability and traceability, entitlements and access controls, data lineage and governance.
Lead delivery of production-grade AI systems with a focus on scalability and reliability, latency and performance optimization, operational readiness and support.
Partner closely with data engineering and platform teams to integrate AI capabilities with Snowflake and Databricks environments, structured and unstructured data pipelines, APIs and enterprise data services, semantic and knowledge-layer architectures.
Requirements
Bachelor’s degree in Computer Science, Engineering, or related field.
10+ years of experience in software engineering, ML engineering, or platform engineering.
3+ years in a leadership role driving complex engineering initiatives or leading teams.
Hands-on experience designing and deploying LLM-based applications, RAG systems, agentic AI workflows, vector databases / semantic search solutions.
Strong understanding of prompt engineering patterns and evaluation methodologies.
Experience with model serving, inference optimization, and production deployment.
Strong background in building scalable, production-grade systems with focus on reliability and observability latency and performance cost optimization.
Familiarity with modern data / AI platforms, including Databricks and/or Snowflake, APIs and microservices architectures, unstructured data processing pipelines, semantic layer or knowledge graph concepts.
Experience working in regulated environments with strong requirements for security and data privacy governance and auditability.
Tech Stack
Microservices
Benefits
Health, dental, vision and life insurance plans
401(k) Savings plan – with generous company matching contributions (up to 6%)
Voya Retirement Plan – employer paid cash balance retirement plan (4%)
Tuition reimbursement up to $5,250/year
Paid time off – including 20 days paid time off, nine paid company holidays and a flexible Diversity Celebration Day.