AI Architect

Siri InfoSolutions Inc; United States; On-site; USD 120,000 - 180,000; Full time

Job summary

Siri InfoSolutions Inc. is seeking a senior AI/ML architecture specialist to design enterprise AI solutions focusing on LLMs, prompt engineering, RAG and agent-driven workflows.

You will shape end-to-end architectures, embedding governance and security-by-design from the ground up. The role requires deep cloud and on-premises experience, Python proficiency, and a track record delivering scalable, observable AI platforms with strong emphasis on reliability, cost efficiency and regulatory

Qualifications

• 3+ years designing and implementing AI/ML or Generative AI solutions in enterprise environments.
• Strong experience with LLMs, prompt engineering, RAG, agent workflows, embeddings, and vector databases.
• Cloud architecture across Azure, AWS or GCP, plus microservices and distributed systems.
• Experience with Python, AI/ML frameworks, DevOps, MLOps/LLMOps, CI/CD.
• Familiarity with AI governance, security reviews, responsible AI standards.
• Experience integrating AI into ITSM, observability, and regulated environments.
• Define end-to-end architecture for enterprise AI solutions including LLM-based applications, RAG, agentic workflows and model orchestration services.
• Design secure, scalable, maintainable and cost-effective AI blueprints across cloud, hybrid and on-premises environments.
• Architect prompt orchestration, contextual grounding, embeddings, vector database integration, retrieval quality, hallucination controls and traceability.
• Embed security-by-design and responsible AI controls covering IAM, API protection, auditability, logging, monitoring, data leakage and prompt injection mitigation.
• Define MLOps/LLMOps, CI/CD, deployment, observability, evaluation framework, production readiness checklist and reusable AI reference architectures.

Responsibilities

• Define end-to-end architecture for enterprise AI solutions including LLM-based applications, RAG, agentic workflows and model orchestration services.
• Design secure, scalable AI blueprints across cloud, hybrid and on-premises environments.
• Architect prompt orchestration, contextual grounding, embeddings, vector database integration, retrieval quality and traceability.
• Embed security-by-design and responsible AI controls covering IAM, API protection, auditing and monitoring.
• Define MLOps/LLMOps, CI/CD, deployment, observability and production readiness.

Skills

LLMs

Prompt engineering

RAG pipelines

Agent workflows

Embeddings & VDBs

APIs & AI services

Cloud architecture

Microservices

Event-driven architecture

Python

MLOps/LLMOps

CI/CD

Security & governance

Responsible AI

ITSM integration

Tools

Azure

AWS

GCP

Vector databases

APIs (REST/GraphQL)

Job description

3+ years hands-on experience designing and implementing AI/ML or Generative AI solutions in enterprise environments.

Strong experience with LLMs, prompt engineering, RAG, agent workflows, embeddings, vector databases and API-based AI services.

Strong cloud architecture knowledge across Azure, AWS or GCP, plus microservices, APIs, distributed systems and event-driven architecture.

Experience with Python, modern AI/ML frameworks, DevOps, MLOps/LLMOps, CI/CD, infrastructure automation, documentation and architecture governance.

Familiarity with AI governance, model risk management, responsible AI standards, security reviews, red teaming, guardrails and adversarial testing.

Experience integrating AI into ITSM, observability, knowledge systems, workflow engines and regulated enterprise environments.

Define end-to-end architecture for enterprise AI solutions including LLM-based applications, RAG, agentic workflows and model orchestration services.

Design secure, scalable, maintainable and cost-effective AI blueprints across cloud, hybrid and on-premises environments.

Architect prompt orchestration, contextual grounding, embeddings, vector database integration, retrieval quality, hallucination controls and traceability.

Embed security-by-design and responsible AI controls covering IAM, API protection, auditability, logging, monitoring, data leakage and prompt injection mitigation.

Define MLOps/LLMOps, CI/CD, deployment, observability, evaluation framework, production readiness checklist and reusable AI reference architectures.