AI Architect - LLM Agent Framework

You are intelligent, skilled, and approachable. A genuine tech professional with a passion for business; an enthusiast who seamlessly tackles tough challenges using the most powerful tools. You're the one who can listen to a client’s technical concerns, and then relay back solutions directly, concisely, and precisely; steering discussions directly to efficient results. You make the complex simple.

As part of the Expedite Commerce team, every day is an opportunity to evolve, advance your career, and unlock your potential while working as part of a close-knit global team of technologists. If you thrive on creating high-performance solutions and excel at solving intricate problems with AWS technologies, we invite you to join us on this dynamic journey.

The Role

As an AI Architect, you will be responsible for designing, building, and fine-tuning NLP models and large language model (LLM) agents to solve business challenges, primarily using AWS Sagemaker and Bedrock technologies. You will play a key role in creating intuitive and efficient model designs that enhance user experiences and business processes. The position demands strong design skills, hands-on coding expertise, advanced proficiency in Python development, specialized knowledge in LLM agent design and development, and exceptional debugging capabilities.

What you will do

You will oversee all aspects of model architecture, data pipeline integration, and metrics interpretation. This includes designing scalable and optimized solutions for training, retraining, deploying, scheduling, monitoring, and improving NLP models and LLM agents. Key responsibilities include:

• Model & Agent Design: Conceptualize and design robust NLP solutions and LLM agents tailored to specific business needs, with a focus on user experience, interactivity, latency, failover and functionality.
• Hands-on Coding: Write, test, and maintain clean, efficient, and scalable code for NLP models and LLM agents, with a strong emphasis on Python programming.
• LLM Agent Development: Develop and fine-tune LLM agents, leveraging advanced techniques in Deep Learning and Transformer architectures, including models like BERT, GPT, Whisper, ChatGPT, and other generative models.
• Performance Monitoring: Monitor, optimize LLM agents, implementing model explainability, handling model drift, and ensuring robustness.
• Research Implementation: Ability to read, comprehend, and implement LLM research papers into practical solutions. Stay abreast of the latest academic and industry research to apply cutting-edge methodologies and techniques.
• Debugging & Issue Resolution: Proactively identify, diagnose, and resolve issues related to LLM models, including model inaccuracies, performance bottlenecks, and system integration problems. Utilize debugging tools and techniques to troubleshoot complex problems in model behavior, data inconsistencies, and deployment errors.
• Innovation and Research: Stay updated with the latest advancements in LLM technologies, experimenting with new techniques and tools to enhance agent capabilities and performance.
• Continuous Learning: Adaptability to unlearn outdated practices, patterns, technologies and quickly learn and implement new technologies & papers as the ML world evolves. Maintain a proactive approach to staying current with emerging trends and technologies in Agent based solution (Text & Multi Modal).

Requirements

• Design Expertise: Demonstrated ability to design complex systems including LLM agents, with experience in architecting solutions from conceptualization to deployment.
• Hands-on LLM based framework & Agent Coding: Extensive experience in coding of LLM agents, with advanced proficiency in Python (3.10+), including knowledge of frameworks such as PyTorch, or similar.
• LLM Agent Design & Deployment: 4-6 years of experience in fine-tuning LLMs and deploying LLM agents, including practical experience with AWS Bedrock, OpenAI Function Calling, Anthropic Function Calling, CrewiAI, Meta GPT framework, and other relevant platforms.
• Strong Python Skillset: Proven track record of developing high-quality, efficient Python code, including experience with advanced Python features and best practices.
• Integration Skills: Experience with integrating open-source and commercial LLM models and LLM agents, including developing and evaluating prompt engineering techniques.
• Advanced LLM Knowledge: Deep understanding of multi-modal model architecture, experience with AWS Bedrock agent models, and practical experience in fine-tuning models for specific use cases.
• Technical Proficiency Strong skills in deploying models and agents on cloud platforms, particularly AWS, and implementing serverless architectures (Utilizing AWS Lambda, Kinesis, SQS, DDB, Bedrock, OpenAI API, S3, Step Function)..
• Debugging & Troubleshooting: Expertise in debugging and fixing issues related to LLMs, including identifying root causes of errors, resolving discrepancies in model outputs, and optimizing system performance.
• Communication Skills:** Excellent written and verbal communication skills in English, with the ability to present technical concepts clearly with team and clients. Should be excelling in designing utilizing mi
• Experience ub CI/CD pipeline using AWS CodePipeline, CodeBuild, and CodeDeploy for automated testing and deployment of NLP Solution.
• Portfolio and Contributions: Demonstrable portfolio of LLM projects and LLM agent developments, with contributions to public forums like Kaggle, open-source projects, and publications in technical forums.
• Experience in understanding latest technologies/papers and implementing the sane into the solution
• Hands-on experience in CI/CD solution utilizing AWS services (Code Commit, Code Build & Code Pipeline)
• Nice to have a good understanding of multimodal solution finetune and deployment.

The Tech Stack

• LLMs and Agent based Models: Expertise in working with large language models (LLMs) like GPT, Claude, Gemini, LLAMA3, Anthropic, and others, including experience in fine-tuning and deploying these models.
• AWS Platform Services: Proficiency in AWS services (Lambda, Step Functions, S3, DynamoDB, SQS, SNS, CloudWatch Logs).
• Serverless Architecture: Experience in designing and implementing serverless solutions.
• Integration Skills: Experience integrating NLP solutions and LLM agents with platforms like Salesforce and using Atlassian agile tools (Jira & Confluence).
• Communication Tools: Proficiency in using Zoom and Gong.io for communication and AI-based analysis.

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

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.