Skip to content
Experience circuit/Sector 01/CAS
0102030405
Sector 01 of 05·IndustryAWS S3 & DynamoDB Agentic Scale

CAS (Chemical Abstracts Service, ACS)

AI and Software Development Intern

Enterprise AI & Cloud Applications

TenureMay 2026 – Aug 2026
LocationColumbus, OH
DisciplineIndustry
Competencies7 Verified

At Chemical Abstracts Service (CAS), a division of the American Chemical Society, engineered full-stack agentic AI and machine learning systems serving scientific product teams. Architected serverless cloud data pipelines across Amazon S3 and Amazon DynamoDB, deployed production Retrieval-Augmented Generation (RAG) graphs with specialized vector databases, and instituted C4 component modeling alongside automated GitLab trunk-based deployment pipelines.

Technical Workstreams & Architecture

3 Core Areas
Workstream 1

Agentic AI & Vectorized RAG Systems

Constructed multi-turn agentic workflows using specialized LLM agents and Claude developer tooling to synthesize unstructured chemical literature, patents, and property registries with sub-second retrieval benchmarks.

Deliverables:
  • ―Deployed hybrid dense/BM25 retrieval pipelines connected to specialized vector databases.
  • ―Formulated deterministic guardrails preventing model hallucination in scientific queries.
  • ―Integrated continuous fine-tuning loops to improve entity extraction recall on chemical nomenclature.
RAGVector DatabasesClaude ToolsPythonLLM Agents
Workstream 2

Serverless Cloud Data Tier & State Persistence

Designed high-throughput, low-latency cloud infrastructure leveraging Amazon Web Services to handle persistent agent memory, stakeholder request queues, and large-scale document transformations.

Deliverables:
  • ―Engineered partition key schemas on Amazon DynamoDB for sub-10ms session cache lookups.
  • ―Provisioned encrypted Amazon S3 pipelines for high-volume scientific document ingestion and pre-processing.
  • ―Implemented least-privilege IAM policies and automated resource monitoring.
Amazon DynamoDBAmazon S3AWS IAMServerless
Workstream 3

C4 Architecture & Trunk-Based Deployment Safety

Authored formal C2 and C4 architectural diagrams to map subsystem boundaries across enterprise engineering teams, establishing clean API contracts and continuous deployment velocity.

Deliverables:
  • ―Structured modular service contracts to eliminate cross-team coordination bottlenecks.
  • ―Instituted automated GitLab CI/CD regression gates enforcing zero typecheck regressions before merge.
  • ―Adopted trunk-based development practices reducing release branch divergence.
C4 ArchitectureGitLab CI/CDTrunk-Based Development

Verified Deliverables & Outcomes

Empirical Evidence
Vector Retrieval
Sub-second

Benchmarked across scientific paper and patent chunk lookups.

Trunk-Based Passing
100%

Zero regression merges through automated GitLab deployment gates.

Architecture Compliance
C2 / C4

Documented component boundaries aligned with enterprise standards.

Charter Achievements:
  • ―Engineered agent-based AI and ML full-stack applications for product stakeholders on AWS S3 and DynamoDB, and deployed agentic AI workflows using vector databases, RAG and model training.
  • ―Streamlined deployment pipelines with trunk-based development through GitLab, using Claude tools and agents.
  • ―Contributed to C2/C4 architecture designs, improving cross-functional development efficiency and quality.
Ground-Truth Evidence:

Technologies & Tooling

Specific tools, libraries, and frameworks leveraged during this tenure:

Amazon S3Amazon DynamoDBAgentic WorkflowsRAGVector DatabasesGitLabC4 Architecture

Engineering Methodologies

Operational practices and systemic disciplines enforced:

Trunk-Based DevelopmentC4 Software ArchitectureRetrieval-Augmented Generation (RAG)Serverless Cloud ArchitectureDefensive Secret & Credential Isolation
Engineering takeaway:
“Enterprise AI is only as trustworthy as the data boundary beneath it. Designing clean DynamoDB partition keys and modeling strict C4 contracts proved far more critical to production reliability than the model weights alone.”