Senior AI Solutions Architect

Veriipro; Chicago (IL); On-site; USD 180,000 - 250,000; Full time

Job summary

Veriipro in Chicago is seeking a Senior AI Solutions Architect to lead the architecture and development of scalable Generative AI, LLM, and RAG solutions. This role combines hands-on Python development with AWS infrastructure to deliver production-grade AI applications.

You will own end-to-end design, mentor engineers, and drive design reviews while translating business needs into scalable architectures and technical plans. A strong background in LLMs and LangChain is essential.

Qualifications

• Hands-on Python and backend development experience.
• Experience with FastAPI or Flask.
• Proven production LLM/Generative AI and RAG delivery.
• Strong knowledge of LLM architectures, embeddings and vector DBs.
• Experience with OpenAI, Anthropic, Hugging Face, LangChain.
• Strong AWS cloud architecture and deployment experience.
• Experience with microservices, APIs, security and scalability.
• Proven ability to lead architecture/design reviews and planning.
• Mentor engineers and influence decisions without formal authority.

Responsibilities

• Own end-to-end architecture and technical design of LLM and Generative AI solutions.
• Translate business requirements into scalable solution architectures, technical plans, and development tasks.
• Define architecture standards, integration patterns, technical decisions, and engineering best practices.
• Provide technical direction, mentor engineers, and lead design and code reviews.
• Design and develop scalable Python APIs and microservices using FastAPI, Flask, or similar frameworks.
• Architect and implement LLM applications, LangChain workflows, and RAG pipelines.
• Define strategies for prompt engineering, embeddings, chunking, retrieval, re-ranking, and model evaluation.
• Design and optimize vector database solutions using Pinecone, Chroma, FAISS, Milvus, or similar technologies.
• Establish monitoring and evaluation for quality, relevance, latency, reliability, safety, and cost.
• Design secure, scalable, and resilient AI services on AWS, including Lambda, EC2, S3, EKS, and RDS.
• Partner with DevOps/MLOps teams on CI/CD, infrastructure automation, observability, incident response, and production support.
• Ensure solutions meet enterprise requirements for security, governance, availability, scalability, fault tolerance, and operational readiness.

Skills

Python

Backend development

Architecture design

LLM/Generative AI

Mentoring engineers

Technical leadership

Code reviews

Prompt engineering

Distributed systems

Security best practices

Tools

FastAPI

Flask

LangChain

OpenAI

Anthropic

Hugging Face

AWS

Pinecone

CI/CD

Kubernetes

Job description

We are seeking a Senior AI Solutions Architect to lead the architecture and development of scalable Generative AI, LLM, and RAG solutions. This is a hands‑on technical leadership role focused on architecture, Python development, AWS, and production AI applications.

Responsibilities

• Own the end-to-end architecture and technical design of LLM and Generative AI solutions.
• Translate business requirements into scalable solution architectures, technical plans, and development tasks.
• Define architecture standards, integration patterns, technical decisions, and engineering best practices.
• Provide technical direction, mentor engineers, and lead design and code reviews.
• Design and develop scalable Python APIs and microservices using FastAPI, Flask, or similar frameworks.
• Architect and implement LLM applications, LangChain workflows, and RAG pipelines.
• Define strategies for prompt engineering, embeddings, chunking, retrieval, re‑ranking, and model evaluation.
• Design and optimize vector database solutions using Pinecone, Chroma, FAISS, Milvus, or similar technologies.
• Establish monitoring and evaluation for quality, relevance, latency, reliability, safety, and cost.
• Design secure, scalable, and resilient AI services on AWS, including Lambda, EC2, S3, EKS, and RDS.
• Partner with DevOps/MLOps teams on CI/CD, infrastructure automation, observability, incident response, and production support.
• Ensure solutions meet enterprise requirements for security, governance, availability, scalability, fault tolerance, and operational readiness.

Required Qualifications

• Extensive software engineering experience with technical leadership responsibilities.
• Strong hands‑on Python and backend development experience.
• Experience with FastAPI, Flask, or comparable frameworks.
• Proven experience delivering production LLM–Generative AI and RAG applications.
• Strong knowledge of LLM architecture, prompt engineering, embeddings, vector databases, retrieval, re‑ranking, and evaluation.
• Experience with OpenAI, Anthropic, Hugging Face, LangChain, or similar platforms/frameworks.
• Strong AWS cloud architecture and deployment experience.
• Experience with microservices, APIs, cloud security, scalability, and distributed systems.
• Strong experience leading architecture/design reviews, code reviews, technical planning, and complex engineering initiatives.
• Ability to mentor engineers and influence technical decisions without formal management authority.

Preferred Skills

• Experience with MLOps, CI/CD, infrastructure as code, and observability.
• Experience with enterprise AI governance, security, and responsible AI practices.
• Experience optimizing AI applications for performance, reliability, and cost.
• Experience working with cross-functional application, data, cloud, security, DevOps, and platform teams.