AI Architect Agentic & Generative AI
Full Time • Dallas TX
Benefits:
- Oppurtunity for Advancement
- Long Term
- Competitive salary
AI Architect Agentic & Generative AI
Dallas, Tx ( Onsite )
Interview: In-Person
As AI Architect – Agentic & Generative AI, you will be responsible for defining, building, and scaling enterprise-grade agentic AI architecture on AWS. This role focuses on establishing frameworks, patterns, and guardrails that enable safe, reliable, and cost-efficient AI solutions, leveraging Amazon Bedrock (Agents, Knowledge Bases, Guardrails, Flows) and Claude models.
You will collaborate with cross-functional teams in product, engineering, data, and security to deliver next-generation AI capabilities — including retrieval-augmented generation (RAG), multi-agent orchestration, and governed AI operations — driving measurable business impact through intelligent automation and decision-making systems.
Responsibilities
Dallas, Tx ( Onsite )
Interview: In-Person
As AI Architect – Agentic & Generative AI, you will be responsible for defining, building, and scaling enterprise-grade agentic AI architecture on AWS. This role focuses on establishing frameworks, patterns, and guardrails that enable safe, reliable, and cost-efficient AI solutions, leveraging Amazon Bedrock (Agents, Knowledge Bases, Guardrails, Flows) and Claude models.
You will collaborate with cross-functional teams in product, engineering, data, and security to deliver next-generation AI capabilities — including retrieval-augmented generation (RAG), multi-agent orchestration, and governed AI operations — driving measurable business impact through intelligent automation and decision-making systems.
Responsibilities
- Define and evolve the enterprise agentic AI architecture, establishing reusable frameworks and standards for RAG, tool/function calling, and multi-agent orchestration.
- Design and implement AI solutions using Amazon Bedrock and integrate with core AWS services (Lambda, Step Functions, EventBridge, ECS/EKS, S3, Aurora, OpenSearch, DynamoDB).
- Drive adoption of agentic AI patterns — planning, memory, and human-in-the-loop — ensuring alignment with enterprise security and compliance frameworks.
- Guide model selection and optimization (Claude family and Bedrock models), including prompt schema design, adapters, and fine-tuning strategies.
- Implement advanced RAG pipelines with optimized chunking, reranking, grounding, and hybrid/vector retrieval using OpenSearch and pgvector.
- Apply Guardrails and data-governance controls (IAM/ABAC, KMS, private networking) to ensure privacy, PII protection, and compliant operations.
- Establish observability and reliability frameworks — including evaluation pipelines, tracing, cost metrics, fallbacks, and A/B testing.
- Collaborate with platform and DevOps teams to enable governed AWS landing zones, CI/CD automation, and environment management for AI workloads.
- Publish architecture blueprints, starter kits, and best-practice guides for AI engineers and developers.
- Mentor engineering teams and contribute to hiring, training, and AI community enablement initiatives.
- Research and assess emerging AWS and open-source agentic tools, proposing pragmatic adoption strategies.
Required Skills & Experience
- 8+ years designing and implementing large-scale distributed or cloud systems (including 4+ years on AWS).
- 2+ years building AI/ML or generative AI solutions in production environments.
- Hands-on experience with Amazon Bedrock (Agents, Knowledge Bases, Guardrails) and Claude models.
- Deep understanding of RAG design, hybrid/vector search (OpenSearch, pgvector), grounding, and citation techniques.
- Proficiency in Python (preferred) or similar modern programming languages.
- Solid grasp of AWS orchestration services (Lambda, Step Functions, EventBridge) and CI/CD practices.
- Applied knowledge of AI governance, security, and observability (IAM, KMS, Guardrails, evaluation, tracing).
- Excellent communication and architectural documentation skills.
Preferred Qualifications
- Expertise in Agentic AI systems, including multi-agent workflows, tool/function calling, and memory architectures.
- Experience with LangChain, LangGraph, or similar orchestration frameworks.
- Advanced prompt design, RAG optimization, and model customization experience.
- AWS Certifications – Solutions Architect (Professional) or Machine Learning Specialty.
Compensation: $70.00 - $75.00 per hour
About Us
We work to deliver profitability in your business – with effective communication, consulting, and interactive solutions. Following an Agile Work Approach, we make sure you get the ideal solutions at minimum expenses.
Work Approach
Our Philosophy
Our Philosophy starts-and-ends at the Client-first approach. Be it understanding your business requirements to choosing the right technologies, we work as a collective team that takes all the possible steps to grow continuously towards our common goal.
Our Philosophy starts-and-ends at the Client-first approach. Be it understanding your business requirements to choosing the right technologies, we work as a collective team that takes all the possible steps to grow continuously towards our common goal.
Work Policy
We promote a collaborative work environment. We involve everyone working in the organization in community decisions and encourage them to think from a broader perspective. Our work process promotes flexibility and we maintain a high level of discipline at different levels of execution.
The Future
SelectMinds have years of experience in the domain helps us understand the need-of-the-hour better. This understanding drives us to a better future with every minute ticking. We believe we will be taking off major businesses from their flagship positions, with the products we are eyeing today.
(if you already have a resume on Indeed)