AI/ML Engineer Internship

The AI/ML Engineer with an AI Agent Focus is a specialized role dedicated to designing, building, and deploying autonomous AI agents that handle complex business processes independently. You will be at the forefront of integrating cutting-edge Large Language Models (LLMs) and reasoning frameworks into our e-commerce and supply chain ecosystem, driving efficiency and innovation through intelligent automation.

Internship Details

Duration: 3 months
Start Date: Immediate
Location: Remote
Stipend: None initially. Based on your first-quarter performance, you may be offered a paid full-time opportunity, or even be absorbed directly by the client as an FTE.

Key Responsibilities & Core Projects

You will be responsible for the full lifecycle of agent development, from initial design to production optimization and monitoring.

• Agent Architecture & Development: Design and build autonomous AI agent architectures utilizing LLMs, advanced reasoning frameworks, and decision-making systems to achieve specific business goals (e.g., customer support automation, sales assistance, workflow optimization).

• Business Process Automation: Create agents that integrate directly into the platform to automate critical supply chain and administrative tasks, such including:

  • Customer Support Agents integrated into the e-commerce storefront.

  • Internal Workflow Automation agents (e.g., Slack integration, Jira automation).

• Multi-Agent Systems: Implement and orchestrate multi-agent systems where specialized agents collaborate to solve complex, multi-step problems across different modules (MES, WMS, OMS).

• Advanced Agent Capabilities: Develop and implement memory systems, sophisticated context management, and tool integration strategies (allowing agents to use internal APIs, search, or code execution) to enhance agent efficacy.

• Model Optimization: Implement techniques for agent improvement, including fine-tuning of LLM models and applying concepts from Reinforcement Learning for optimal decision-making.

• Safety & Monitoring: Implement safety guardrails, define ethical usage guidelines, and build robust monitoring systems (collaborating with MLOps) to track and analyze agent behavior and performance in production.

Required Technologies & Tools

Candidates must possess deep experience in machine learning, LLM technology, and production deployment:

• LLM/Agent Frameworks: Mandatory hands-on expertise with agent construction frameworks like LangChain, LlamaIndex, and AutoGen.

• Programming & ML: Expert proficiency in Python and standard ML/Deep Learning libraries (e.g., PyTorch, TensorFlow).

• Data & APIs: Experience preparing data for model fine-tuning and integrating agents via API endpoints into production services (Node.js/NestJS).

• Deployment: Familiarity with MLOps concepts (versioning, deployment) and containerization (Docker) for agent deployment.

• Databases: Understanding of vector databases and retrieval augmented generation (RAG) techniques.

Supply Chain Integration (Domain Focus)

You will integrate intelligent agents directly into our core supply chain and data systems.

• Data Analysis Agents: Build agents capable of complex data analysis and insight generation using aggregated data from MES, WMS, and OMS.

• E-commerce Integration: Deploy agents that assist users directly within the e-commerce platform by accessing real-time catalog and inventory data.

Success Metrics & Career Path

Performance will be measured by:

• Agent Autonomy: Measurable increase in the percentage of business tasks handled end-to-end by autonomous agents.

• Business Impact: Quantifiable improvements in metrics driven by the agents (e.g., reduced customer support response time, increased sales conversion).

• Model Performance: Accuracy and efficiency of fine-tuned models and the reliability of multi-agent systems.

Mentorship Structure: Reports to the Head of Technology/CTO, working closely with the Data Architect and MLOps Engineer to productionize and scale agent capabilities.