Lead Applied AI Engineer

Northern Base; New York (NY); On-site; USD 170,000 - 210,000; Full time

Job summary

Northern Base is seeking a Lead Applied AI Engineer to architect and deliver production‑grade AI systems that integrate Generative AI capabilities, AI agents, and modern enterprise platforms. You will define technical standards, lead enterprise AI adoption, and mentor engineering teams across architecture, deployment, and governance domains.

You will drive scalable AI solutions with responsible AI practices, observability, and cost optimization, ensuring reliability and security while aligning

Qualifications

• Lead enterprise AI adoption and mentor engineering teams.
• Define engineering standards, prompt engineering, testing methodologies and evaluation frameworks.
• Establish performance optimization strategies for model selection, caching and resource use.

Responsibilities

• AI Solution Architecture: design end‑to‑end AI systems with RAG pipelines and multi‑model integrations.
• AI Engineering Standards & Optimization: set standards for prompts, templates, testing and evaluation; optimize performance and costs.
• Production Deployment & Reliability: deploy AI solutions with observability, logging, tracing and incident response.
• Data & Retrieval Architecture: build scalable data ingestion, vector stores, hybrid search and data quality checks.
• AI Evaluation & Continuous Improvement: implement AB testing, benchmarks and telemetry‑driven optimization.
• Platform & Infrastructure Collaboration: coordinate with GPU infra, model serving, feature stores and scalable storage.
• Technical Leadership & Mentoring: guide architecture reviews, code reviews and career development.
• Responsible AI & Compliance: ensure governance, documentation and fairness/transparency.

Job description

We are seeking an accomplished Lead Applied AI Engineer to architect and deliver advanced AI systems that seamlessly integrate Generative AI capabilities, AI agents, and modern enterprise platforms.

This role is responsible for designing, building, deploying, and scaling production‑grade AI solutions that support large-scale business operations while maintaining high standards of security, reliability, governance, and responsible AI practices.

The Lead Applied AI Engineer will define technical standards, lead enterprise AI adoption, establish engineering best practices, and mentor engineering teams. This position operates at the intersection of AI innovation, enterprise architecture, platform engineering, and responsible AI governance.

Key Responsibilities

AI Solution Architecture

Architect comprehensive end-to-end AI systems including:

• Advanced RAG (Retrieval-Augmented Generation) pipelines
• Multi-stage retrieval and re‑ranking architectures
• Agent orchestration frameworks coordinating multiple specialized agents
• Multi-model AI integrations leveraging model-specific strengths

Design solutions with modularity, extensibility, scalability, and operational excellence to support evolving business requirements.

AI Engineering Standards & Optimization

Define enterprise standards for:

• Prompt engineering
• Prompt templates and versioning
• Testing methodologies
• Evaluation frameworks

Establish performance optimization strategies covering:

• Model selection criteria
• Caching patterns
• Resource utilization
• Cost optimization

Production Deployment & Reliability

Lead deployment of AI solutions into production environments with:

• Comprehensive observability
• Logging and tracing
• Reliability engineering practices
• Graceful degradation mechanisms
• Circuit breaker implementation
• Real‑time monitoring dashboards
• Automated alerting
• Incident response procedures

Ensure AI services meet stringent service‑level objectives and enterprise reliability expectations.

Data & Retrieval Architecture

Design scalable data ingestion frameworks that process:

• Structured data sources
• Unstructured documents
• Real‑time event streams

Develop:

• Vector database architectures
• Hybrid search capabilities
• Data preprocessing pipelines
• Data quality monitoring frameworks

Ensure high‑quality inputs for AI systems through cleansing, enrichment, and governance processes.

AI Evaluation & Continuous Improvement

Establish quantitative evaluation frameworks for AI systems.

Implement:

• A/B testing capabilities
• Performance benchmarking
• User feedback analysis
• Telemetry‑based optimization

Drive continuous improvements across:

• Prompts
• Retrieval strategies
• Agent workflows
• Model configurations

Platform & Infrastructure Collaboration

Partner with platform and infrastructure teams to ensure readiness for AI workloads, including:

• GPU infrastructure
• Model serving platforms
• Feature stores
• Scalable data storage
• Networking infrastructure

Define requirements for enterprise AI platform capabilities and integration patterns.

Technical Leadership & Mentoring

Mentor engineers through:

• Architecture reviews
• Design guidance
• Code reviews
• Career development support

Promote engineering excellence through:

• Best‑practice documentation
• Technical training
• Communities of practice

Foster a culture of responsible and ethical AI development.

Responsible AI & Compliance

Ensure AI solutions adhere to enterprise governance and compliance requirements.

Maintain documentation of:

• System behavior
• Decision logic
• Evaluation methodologies

Apply responsible AI principles including:

• Fairness
• Transparency