Data Science Student Experience

Jobtailor; Buford (ND); On-site; USD 25,000 - 36,000; Part time

Benefits offered by this job

Remote learning access

Mentorship program

Job summary

Jobtailor is seeking interns to collaborate with product managers to translate user needs into AI agent specifications. You will implement NLU, intent detection, and dialogue management using large language models, and build REST/GraphQL endpoints to connect agents with CRM/ERP systems and public APIs.

The role involves writing tests, designing data models, creating automated pipelines, and exploring RAG techniques with vector search tools.

Qualifications

• Freshman to Senior standing pursuing a bachelor’s degree in CS, Data Science, or Engineering.
• Familiarity with Python and JavaScript/TypeScript is a plus.
• Experience with SQL/NoSQL, ETL pipelines, and pandas/Spark is a plus.
• Familiarity with REST/GraphQL services is a plus.
• Able to commit to the Bobcat co-op for 8 months or internship 4 months.

Responsibilities

• Analyze user needs with product managers to identify business pain points and translate into functional specifications for intelligent agents.
• Implement natural language understanding, intent detection, and dialogue management using Large Language Models.
• Build and test REST/GraphQL endpoints connecting agents to CRM, ERP, and public APIs.
• Write unit and integration tests and troubleshoot agent pipeline performance and correctness issues.
• Design knowledge-base schemas and data models.
• Create automated pipelines to ingest, clean, and update documents.
• Research and implement Retrieval Augmented Generation (RAG) techniques and pipelines.
• Deploy vector search solutions such as FAISS, Pinecone, Milvus.
• Develop ranking and optimization logic to improve search-result relevance.
• Package AI agents in Docker containers and deploy them to AWS cloud environments.
• Set up monitoring metrics using CloudWatch or Prometheus and learn incident response.
• Collect user feedback, analyze usage data, and continuously improve agent performance and user satisfaction.

Skills

Natural Language Understanding

Intent Detection

Dialogue Management

REST Endpoints

GraphQL Endpoints

Unit Testing

Integration Testing

Data Modeling

Automated Pipelines

Vector Search Solutions

Python

JavaScript/TypeScript

AWS Services

Docker

Education

Bachelor's degree in Computer Science / Data Science / Engineering (pursuing)

Tools

AWS

Docker

CloudWatch

Prometheus

FAISS

Pinecone

Milvus

Pandas

Spark

Job description

• Analyze user needs with product managers to identify business pain points and translate them into functional specifications for intelligent agents


• Implement natural language understanding, intent detection, and dialogue management using large language models


• Build and test REST/GraphQL endpoints connecting agents to CRM, ERP, and public APIs


• Write unit and integration tests and troubleshoot agent pipeline performance and correctness issues


• Design knowledge-base schemas and data models


• Create automated pipelines to ingest, clean, and update documents


• Research and implement Retrieval Augmented Generation (RAG) techniques and pipelines


• Deploy vector search solutions such as FAISS, Pinecone, or Milvus


• Develop ranking and optimization logic to improve search-result relevance


• Package AI agents in Docker containers and deploy them to AWS cloud environments


• Set up monitoring metrics using CloudWatch or Prometheus and learn incident response


• Collect user feedback, analyze usage data, and continuously improve agent performance and user satisfaction

Requirements

• Freshman, Sophomore, Junior or Senior standing seeking a bachelor’s degree in Computer Science, Data Science, Engineering, etc.


• Familiarity with Python and JavaScript/TypeScript is a plus


• Familiarity with SQL/NoSQL, ETL pipelines, and data-processing libraries such as pandas and Spark is a plus


• Familiarity with building or consuming REST/GraphQL services is a plus


• Familiarity with AWS services including Bedrock, S3, Lambda, and SageMaker, or equivalent, is a plus


• Ability to commit to Bobcat for the entire co-op term (8 months) or internship term (4 months)


• Attention to detail


• Team player, fast learner, and adaptable to change


• Excellent interpersonal and communication skills


• Self-starter able to investigate problems independently with limited guidance


• Ability to follow written instructions

Core Competencies

Proficient in Natural Language Understanding, Intent Detection, and Dialogue Management using Large Language Models, with experience in building and testing REST/GraphQL endpoints and deploying AI agents in AWS environments. Strong analytical skills for translating user needs into functional specifications and optimizing search-result relevance.

Highest-signal resume keywords

• Natural Language Understanding


• REST/GraphQL Services


• AWS Services


• Python Programming


• Data Processing Libraries

Hard Skills

• Natural Language Understanding


• Intent Detection


• Dialogue Management


• REST Endpoints


• GraphQL Endpoints


• Unit Testing


• Integration Testing


• Data Modeling


• Automated Pipelines


• Vector Search Solutions

Soft Skills

• Attention to Detail


• Team Player


• Fast Learner


• Excellent Communication Skills


• Self-Starter

Industry Keywords

• Data Science


• Computer Science


• Engineering


• ETL Pipelines


• User Feedback Analysis

Tools & Technologies

• AWS


• Docker


• CloudWatch


• Prometheus


• FAISS


• Pinecone


• Milvus


• Pandas


• Spark