LLM Agent Engineer

Be at the forefront of AI innovation — designing intelligent agents that transform how businesses engage with customers.

At Expedite Commerce, we’re redefining the future of commerce through agentic AI — systems that reason, act, and learn. You’ll help build these next-gen agents, shaping real-world impact from concept to deployment.

You’ll collaborate with brilliant teammates across product, design, and engineering — turning bold ideas into elegant, scalable solutions that streamline workflows and elevate customer experiences.

If you’re passionate about building smarter AI systems and want your code to power real change, this is where you belong.

What You’ll Do

You’ll be at the center of how Expedite Commerce builds the next generation of intelligent, serverless AI ecosystems.

• Design & develop LLM-powered agents using frameworks like OpenAI Agents SDK and Strands Agents SDK.
• Implement tool orchestration, contextual memory, reasoning chains, and feedback-learning loops that make agents smarter with every interaction.
• Build multi-agent systems — where agents communicate (A2A), share context/state, and coordinate actions via the Model Context Protocol (MCP).
• Deploy at scale — design serverless agent platforms using AgentCore/Gateway, integrate tools (REST APIs, MCP servers), and build event-driven systems with API Gateway, DynamoDB, S3, and Kinesis.
• Code in Python and containers: package serverless functions into Docker images, optimize for performance, cost, and observability.
• Own the lifecycle: from POC to production, balancing speed, quality, and innovation under delivery pressure.
• Collaborate deeply with AI research, backend engineering, and product design teams to shape internal SDKs, frameworks, and agent standards.

This is your chance to build what doesn’t exist yet — defining how autonomous AI agents will power the enterprise.

Requirements

What You Bring to the Team

• You’ve spent at least a year in agentic AI, designing and deploying systems where agents reason, act, and learn autonomously.
• You know your way around AWS serverless — from Lambda, AWS Step Function, Redis, Open Search, API Gateway , DynamoDB, Kinesis, and S3 — and can spin up event-driven agentic AI architectures that scale beautifully.
• You’ve built and shipped with OpenAI Agents SDK or Strands Agents SDK, and you’re fluent in the language of multi-agent orchestration (A2A, shared context, MCP tools).
• Python is your playground — you write clean, efficient code, package it into Docker containers, and get it running in production with confidence.
• You think beyond code — about latency, cost, observability, and performance — and you design systems that are as elegant as they are efficient.
• You understand that great agents don’t just work — they improve. You know how to design feedback loops, fine-tune reasoning, and measure outcomes.
• You have implemented RAG pipelines, knowledge graphs, vector stores to power contextual memory and smarter decision-making into Agentic AI solution
• Familiarity with AgentCore/Gateway or similar frameworks? That’s a major plus
• Communication Skills: Excellent verbal and written communication skills that foster collaboration and engagement.
• Creativity & Curiosity: A genuine curiosity for emerging technologies and a talent for coming up with creative solutions to complex problems.
• Adaptability: Thrives in a fast-paced environment and can pivot quickly while maintaining a positive attitude.

Work Timings - 1 pm -10 pm IST

Benefits

• Health Insurance, PTO, and Leave time

• Ongoing paid professional training and certifications
• Fully Remote work Opportunity
• Strong Onboarding & Training programs

Next Steps

We’re looking for someone who embodies the spirit of a boundary-pushing LLM Engineer — ready to design intelligent agents, scale multi-agent architectures, and integrate AI where it truly transforms outcomes.

• Apply Now:
  Send us your resume and a brief summary of your experience building or leading LLM-driven systems, including notable multi-agent, serverless, or AI automation projects.
• Show Us Your Ingenuity:
  Be ready to share examples of your smartest agent designs — how you combined reasoning, tool use, and orchestration to deliver real results, and how you overcame complex AI or scalability challenges.
• Collaborate & Ideate:
  If selected, you’ll join a live workshop with our AI leadership team to explore a real-world agent architecture scenario — we’ll look for your ability to reason, design, and iterate under open-ended, high-impact conditions.

This is your opportunity to shape the future of intelligent systems — building autonomous agents that power enterprise-scale workflows across AWS, AI platforms, and beyond.
We can’t wait to see what you’ll create.

Our Belief

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

If this resonates with you—if you’re driven, daring, and ready to build the next wave of multi-platform 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 G2/products/expedite-commerce, 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.