Llm Agent Engineer

closed
Expedite Commerce Logo

Expedite Commerce

πŸ“Remote - India

Summary

Join a forward-thinking team reshaping how businesses leverage AI. Develop and fine-tune large language model (LLM) agents transforming entire businesses. Craft next-generation LLM agent solutions using AWS technologies like SageMaker, Bedrock, Lambda, and more. Collaborate with a team driven by bold risks, creativity, and user-centric innovation. Design, build, deploy, and continuously improve LLM agents tackling real-world challenges. Shape the future of AI with scalable, serverless, multi-agent systems.

Requirements

  • Hands-on experience in developing and deploying LLM agents with advanced features like tool integration, contextual memory systems, and feedback-driven learning using a custom agent framework
  • Demonstrated expertise in designing and implementing multi-agent systems, enabling agents to collaborate and solve complex tasks efficiently
  • Experience in building robust inter-agent communication protocols to ensure seamless coordination between multiple agents
  • Skilled in designing systems for state transfer and context preservation across multiple agents, ensuring consistent and accurate task execution
  • Experience leveraging AWS Bedrock and related AWS services to build efficient and scalable solutions
  • Familiarity with deploying agents in Docker containerized environments and adhering to best practices
  • Keeps up with advancements in LLMs, experimenting with and implementing new techniques to solve real-world challenges
  • Thrives in a fast-paced environment by learning new methods and unlearning outdated practices
  • Proficient in AWS services such as Lambda, Step Functions, DynamoDB, S3, and Kinesis to build event-driven solution stack
  • Experience in maintaining CI/CD pipelines using AWS tools like CodePipeline, CodeBuild, and CodeDeploy
  • Experience in monitoring and optimizing deployment costs, with a focus on identifying inefficiencies and implementing resource-saving strategies

Responsibilities

  • Develop and fine-tune large language model (LLM) agents
  • Craft next-generation LLM agent solutions using AWS technologies like SageMaker, Bedrock, Lambda, Step Functions, DynamoDB, and Kinesis
  • Leverage these tools for real-time data insights, enabling seamless inter-agent communication, state transfer, and memory handling
  • 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 with cross-functional teams to integrate LLM agents into AWS-driven infrastructures
  • 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
  • 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
  • Influence not just the technology stack, but the very way people interact with AI
  • Help craft solutions that endure, shaping the next wave of agent-based design across multiple verticals

Preferred Qualifications

Familiarity with Terraform

Benefits

  • Health Insurance
  • PTO
  • Leave time
  • Ongoing paid professional training and certifications
  • Fully Remote work Opportunity
  • Strong Onboarding & Training program
This job is filled or no longer available

Similar Remote Jobs