AI Solution Architect

Lorven Technologies Inc.; New York (NY); On-site; USD 140,000 - 210,000; Full time

Job summary

Lorven Technologies Inc. in Manhattan, NY is seeking an experienced AI Solution Architect to architect and deliver enterprise-grade AI/ML, Generative AI, and Agentic AI solutions using Spec-Driven Engineering practices.

The role combines deep architecture expertise with hands-on AI engineering, cloud-native design, and the ability to translate complex business requirements into secure, scalable, production-ready AI systems.

Qualifications

• Strong understanding of ML, DL, Generative AI, LLMs/SLMs, RAG, Agentic AI, prompt engineering, embeddings, vector search, AI evaluation.

Responsibilities

• Architect end-to-end enterprise AI solutions spanning data ingestion, model/LLM integration, retrieval, orchestration, deployment, evaluation and governance.
• Design Generative AI, RAG, and Agentic AI solutions.
• Define Architectures incorporating agent orchestration, tool/API integration, memory management, guardrails, and observability.
• Evaluate and select LLMs/SLMs, embedding models, frameworks, retrieval approaches, and deployment patterns.

Skills

ML concepts

Python & ML frameworks

Cloud platforms (Azure, AWS, GCP)

Data tech (Kafka, Spark, Airflow)

MLOps / LLMOps

APIs & microservices

Spec-Driven Engineering

Stakeholder leadership

Knowledge graphs & Graph-RAG

Tools

Docker

Kubernetes

Terraform

CI/CD

GitOps

MLflow

Job description

Location: Manhattan, NY (NY/ NJ talents are preferred)

Full time permanent

We are looking for an experienced AI Solution Architect to architect and deliver enterprise-grade AI/ML, Generative AI, and Agentic AI solutions using Spec-Driven Engineering practices. The role requires a combination of strong architecture expertise, hands‑on AI engineering knowledge, cloud‑native solution design, and the ability to translate complex business requirements into secure, scalable, production‑ready AI solutions through clear, testable, and traceable specifications.

Required Skills

• Strong understanding of Machine Learning, Deep Learning, Generative AI, LLMs/SLMs, RAG, Agentic AI, prompt/context engineering, embeddings, vector search, structured outputs, and AI evaluation techniques.
• Strong hands‑on knowledge of Python and AI/ML frameworks such as PyTorch, TensorFlow, Hugging Face, LangChain, LangGraph, or CrewAI.
• Experience with enterprise AI and cloud platforms such as Azure AI Foundry/Azure Machine Learning, AWS SageMaker and related AWS AI services, or Google Vertex AI.
• Knowledge of SQL, NoSQL, vector databases, graph databases, knowledge graphs, and data/platform technologies such as Kafka, Spark, and Airflow.
• Experience with cloud‑native engineering and MLOps/LLMOps, including Docker, Kubernetes, Terraform, CI/CD, GitOps, MLflow or equivalent lifecycle and observability platforms.
• Strong understanding of REST/GraphQL APIs, microservices, event‑driven architectures, distributed systems, enterprise integration patterns, and architecture for security, privacy, resiliency, scalability, performance, observability, and cost optimization.
• Experience with Spec-Driven Engineering, including requirements decomposition, architecture and API specifications, executable acceptance criteria, specification‑to‑code/test traceability, version control, and AI‑assisted engineering workflows.
• Strong client‑facing solutioning, stakeholder management, technical leadership, architecture documentation, and communication skills, with experience designing AI solutions for regulated industries.
• Knowledge of knowledge graphs, ontologies and Graph‑RAG architectures

Key Responsibilities

• Architect end-to-end enterprise AI solutions spanning data ingestion, model/LLM integration, retrieval, orchestration, application integration, deployment, evaluation, monitoring, and governance.
• Design Generative AI, RAG, and Agentic AI solutions.
• Define Agentic AI architectures incorporating agent orchestration, tool/API integration, context and memory management, human‑in‑the‑loop controls, guardrails, evaluation, and observability.
• Evaluate and select appropriate LLMs, SLMs, embedding models, AI frameworks, retrieval approaches, and deployment patterns based on accuracy, latency, security, scalability, and cost.
• Architect AI solutions using services across AWS, Microsoft Azure, and Google Cloud, with deep expertise in at least one hyperscaler.
• Design cloud‑native and distributed architectures using APIs, microservices, event‑driven patterns, containers, and Kubernetes.
• Define enterprise AI security and governance controls covering identity and access, data privacy, responsible AI, model security, auditability, and regulatory requirements.
• Lead solution discovery, architecture definition, technical assessments, POCs, reference architectures, reusable accelerators, and productionization.
• Drive Spec-Driven Engineering across the AI solution lifecycle by translating business intent, architecture decisions, functional and non-functional requirements, interfaces, guardrails, and acceptance criteria into version-controlled, machine-consumable specifications that guide design, code generation, testing, validation, and deployment.
• Partner with business stakeholders, enterprise architects, product teams, data scientists, AI engineers, DevOps/platform teams, and security teams.
• Provide technical leadership, conduct architecture/design reviews, mentor engineering teams, and communicate solution trade-offs to technical and executive stakeholders.