Unconventional LLM Agent Architect - Harnessing AWS for Next-Gen Agent Solutions

This Is No Ordinary Role. This Is No Ordinary Code.

This is for people who have something to prove. For those who’ve shattered the status quo, crafted ingenious AI architectures, and crave a chance to reshape what’s possible in an AI-first, high-growth environment.

What if YOU could architect and fine-tune large language model (LLM) agents that transform entire businesses?

What if you could do it with cutting-edge AWS technologies like SageMaker and Bedrock, real-time data insights, and a team that lives for bold risks, creativity, and user-centric innovation?

Sounds exciting?
Maybe you’re ready to leap in with both feet. But before you do, ask yourself:

• Are you truly an innovator, unafraid to break apart old assumptions and design AI solutions that challenge the norm?
• Are you user-obsessed, building experiences that delight while driving business growth?
• Can you think differently—and code differently—using the latest research in NLP and generative AI to amplify results?
• Do you embrace calculated risks, learning and adapting from each iteration?
• Are you hungry to leave a legacy—not just for one product, but for a growing ecosystem of AI-powered transformations?

About Us

We’re a forward-thinking team on a mission to reshape how businesses leverage AI. Our approach is laser-focused on creating transformative NLP solutions, harnessing the power of LLMs, and optimizing them with AWS Sagemaker, Bedrock, and beyond. We don’t just design models—we build experiences and ecosystems that redefine user interactions and business processes.

Why This Role Is Different

Design Your Impact
Don’t just fine-tune a model—own the entire architecture. Conceptualize, build, deploy, and continuously improve LLM Agents that tackle real-world challenges and drive measurable outcomes. Leverage AWS services such as Container, Lambda, and Bedrock to create scalable, serverless solutions, enabling agents to operate with precision and reliability.

Collaborate to Innovate
Work side-by-side with a forward-thinking leadership team that values experimentation, continuous learning, and radical transparency. Collaborate with cross-functional teams to integrate LLM agents into AWS-driven infrastructures, fostering innovative approaches to problem-solving while maintaining a customer-first perspective. We want your bold ideas and your willingness to challenge our assumptions.

Build Across Ecosystems
.Design and deploy LLM Agents that scale across business lines, leveraging AWS tools like API Gateway, Step Functions, and DynamoDB for seamless integration into diverse products, services,

Leverage AI First
Utilize cutting-edge generative models, AWS AI/ML services, and AI-powered IDEs to develop and deploy LLM Agents, optimizing performance, scalability, and real-time application outcomes.

Leave a Legacy
Influence not just the technology stack, but the very way people interact with AI. You’ll help craft solutions that endure, shaping the next wave of agent-based design across multiple verticals.

Requirements

Proven LLM & Agent Architecture

• Architecture Mastery: You’ve taken LLM agent-based solutions from concept to production, excluding frameworks like LangChain and Crew.ai, with a focus on scalable, serverless agent solutions built on AWS. Expertise in optimizing latency and ensuring high availability for seamless performance.
• Hands-On Agent Development: 4 4-6 years of experience designing LLM-based agents with capabilities like tool integration, memory, planning, and feedback-driven learning, leveraging AWS Bedrock and deploying in containerized environments such as Docker.
• Python & Beyond: You’re fluent in Python (3.10+), including advanced features, testing, debugging, and integration best practices.
• LLM Agent Monitoring and Self-Improvement: Skilled in generative monitoring of LLM agents for real-time performance tracking and feedback-driven self-improvement. Expertise in enhancing agent behavior, accuracy, and efficiency to align with dynamic use cases and business needs.
• LLM Agent Cost Monitoring & Optimization: Extensive experience in monitoring and optimizing the cost of LLM agent deployments, with a focus on identifying inefficiencies, managing resource utilization, and implementing cost-saving strategies in serverless architectures.

Innovative Problem-Solving

• Research at the Ready: You keep up with the latest LLM and Deep Learning breakthroughs. You read papers, experiment, iterate, and turn theoretical concepts into real-world tools.
• Continuous Learning: You love unlearning outdated patterns just as much as mastering new techniques. This field is always evolving, and so are you.

AWS Serverless Scalable Solutions

• Serverless Proficiency: AWS Lambda, Docker Container, AWS Step Functions, S3, DynamoDB, Kinesis, SQS—these aren’t just buzzwords; they’re part of your everyday toolkit for building robust, event-driven architectures.
• CI/CD Aficionado: 3–4 years of experience designing and implementing AWS CI/CD pipelines using Terraform, CodePipeline, CodeBuild, and CodeDeploy for automated provisioning, LLM agent deployment, and seamless cloud integration. Proficient in automating deployments, testing, and monitoring to streamline workflows, enhance performance, and ensure reliability..
• Terraform, IAC: These aren’t just tools; they’re the backbone of your streamlined, automated infrastructure. From defining modular blueprints to provisioning scalable, fault-tolerant systems, IaC isn’t just a practice—it’s how you bring infrastructure to life with precision and reliability.

Culture Fit

• Bold Risk-Taking: You thrive in an environment that encourages calculated experimentation and embraces occasional failures as opportunities to learn.
• Team Collaboration: You communicate effortlessly with diverse teams and client stakeholders, championing clarity, empathy, and knowledge-sharing.

Benefits

• Health Insurance, PTO, and Leave time
• Ongoing paid professional training and certifications 
• Fully Remote work Opportunity
• Strong Onboarding & Training program

Work Timings - 1 pm -10 pm IST

Next Steps

We’re looking for someone who already embodies the spirit of a boundary-breaking AI Architect—someone who’s ready to own ambitious projects and push the boundaries of what LLMs can do.

1. Apply Now: Send us your resume and answer a few key questions about your experience and vision.
2. Show Us Your Ingenuity: Be prepared to talk shop on your boldest AI solutions and how you overcame the toughest technical hurdles.
3. Collaborate & Ideate: If selected, you’ll workshop a real-world scenario with our team—so we can see firsthand how your mind works.

This is your chance to leave a mark on the future of AI—one LLM agent at a time. We’re excited to hear from you!

Our Belief

We believe extraordinary things happen when technology and human creativity unite. By empowering teams with generative AI, we free them to focus on meaningful relationships, innovative solutions, and real impact. It’s more than just code—it’s about sparking a revolution in how people interact with information, solve problems, and propel businesses forward.

If this resonates with you—if you’re driven, daring, and ready to build the next wave of AI innovation—then let’s do this. Apply now and help us shape the future.

About Expedite Commerce

At Expedite Commerce, we believe that people achieve their best when technology enables them to build relationships and explore new ideas. So we build systems that free you up to focus on your customers and drive innovations. We have a great commerce platform that changes the way you do business!

See more about us at expeditecommerce.com. You can also read about us on https://www.g2.com/products/expedite-commerce/reviews, and on Salesforce Appexchange/ExpediteCommerce.

EEO Statement

All qualified applicants to Expedite Commerce are considered for employment without regard to race, color, religion, age, sex, sexual orientation, gender identity, national origin, disability, veteran's status or any other protected characteristic.