Machine Learning Intern @ Coalition Inc. – New York, NY (June 2025 – Dec 2025)

Built an org-wide Document Classification Service on AWS (SageMaker, S3) to automate claims processing for the Manual Submissions team, replacing a rigid legacy model with a modular system capable of identifying loss runs, financial statements, and signatures.

Achieved 99% accuracy (up from 79%) in document categorization by implementing Chain-of-Thought (CoT) prompting and designing rigorous evaluation pipelines using MLflow and Python.

Reduced token consumption by 40% and lowered overall inference costs by refactoring output logic (removing JSON brackets) and identifying cost-efficiencies in migrating to newer NLP models.

Deployed a unified API endpoint integrating Regex brand classifiers and LLMs, enabling the broader engineering organization to access scalable document intelligence tools.

Founding Engineer @ Mavn AI – New York, NY (March 2024 – Jun 2025)

Architected and maintained the core infrastructure for an ML data platform serving enterprise clients (e.g., V7 Labs, DataCurve), scaling system throughput to support $50k MRR with 99.9% uptime.

Optimized PostgreSQL performance to handle high-concurrency write loads from 150+ simultaneous annotators; implemented custom indexing strategies that reduced p99 query latency by 40% during peak traffic.

Engineered a low-latency code execution sandbox in C++ using Linux namespaces and seccomp filters (via Google Sandbox2), enabling the secure, isolated evaluation of untrusted user code on bare-metal EC2.

Engineered production-grade data pipelines on Kubernetes and AWS SageMaker, automating the secure ingestion, versioning, and fine-tuning of datasets to support rapid model iteration cycles.

Designed a distributed quality assurance system using TypeScript and LangChain agents, removing manual verification bottlenecks and ensuring data consistency across distributed engineering teams.

Software Engineer Intern @ Scale AI – Remote (Jan 2024 – March 2024)

Engineered multi-stage QA pipelines for LLM training data, designing consensus algorithms and automated conflict resolution logic that improved dataset accuracy from 91% to 98%.

Developed automated validation frameworks using Python, Pandas, and Scikit-learn, implementing statistical checks to detect anomalies and rank annotator performance at scale.

Software Engineer @ Ignite Local – Remote (Jul 2021 - Jan 2024)

After my internship, I stayed on a contract basis to build a proprietary Python-based CMS and automated deployment infrastructure on GCP to centrally manage and scale production for over 300 client websites.

Scaled web production capabilities, automating the deployment of 300+ responsive websites built with React and TypeScript while ensuring cross-browser compatibility.

Software Engineer Intern @ Ignite Local – Remote (May 2021 – Jul 2021)

Developed Python automation scripts to aggregate and clean client performance data, reducing manual reporting time by 30% and enabling the product team to track key engagement KPIs in real-time.

Contributed to web development and component design in React (TypeScript), leading to a return offer for a contractor based software engineering role.