Nathan Lara
Background

Experience

Professional roles and the stack I build with. See also leadership & awards and the résumé.

Professional

Jun – Aug 2026
New York, NY

AI Product Builder

BCG X

Boston Consulting Group · New York, NY

  • Owned the web product for the CFS Builder Toolkit — BCG's reusable-AI-component platform for the Corporate Finance & Strategy practice (Project Helix) — migrating it from a standalone prototype into the practice's production platform (Next.js/TypeScript) and taking it live, and rebuilding the application end to end (ten tabs to three) on one engine serving both its build-a-tool and direct-answer paths.
  • Added the pieces that decided whether it got used twice — per-user work persistence, so an in-progress assessment survives a reload or a re-login instead of being lost, and CSV/Excel export where numbers land as real numbers a consultant can chart without retyping.
  • Hardened the platform ahead of launch — allowlist access gating with a request-to-access flow across roughly 170 users, its API routes secured under a maintainer-versus-admin permission model, and each change regression-locked before it merged.
  • Gated a contract-restricted data source out of the model's autonomous reach with a fail-closed control enforced at a single shared seam, so one rule holds across the web app, the hosted MCP connector, and the desktop client at once.
  • Shipped seven canonical bring-your-own-key modules into the practice's common data layer — SEC EDGAR/XBRL, FRED, Statista, Crunchbase, Inven, plus two BCG-proprietary internal sources built from scratch — each verified against live APIs, and proved out the server-side bring-your-own-key model, demonstrating credential containment and non-exfiltration under adversarial instruction.
  • Built the platform's first quality rubric and automated evaluation harness (TypeScript/Vitest, 27 to 120 tests), including the ground-truth benchmark that replaced a flattering 71% retrieval score on synthetic prompts with a real ~15% against actual builds — then rebuilt retrieval from flat keyword overlap to BM25 with field-weighting and stemming, lifting it to ~90% recall and catching broken cross-references across 37% of the catalog.
May 2026 – Present
Remote

Independent Contractor — AI & Content

OCI Group Consulting

Remote

  • Designed and delivered an 8-module AI enablement program for the firm's partners — deployed as a self-serve web portal (Vercel), not a slide deck — covering Gemini/Claude/ChatGPT workflows, prompt engineering, and AI governance, tailored live to their actual stack.
  • Created the credentials deck the firm used in a live pitch for a role on a multi-billion-dollar development project — synthesizing a dozen+ conflicting source proposals into one narrative across 11 client-feedback revisions; the deck advanced the partnership and is being productized into a reusable template.
Jan – May 2026
New York, NY

AI Agent Developer

PwC

Capstone Project × Fordham

  • Automated end-to-end M&A deal monitoring across 51 live sources via a RAG pipeline (LangChain, Chroma, GPT-4o) with 8-K parsing, MD5 dedup, and daily scheduling.
  • Engineered a structured extraction and SEC XBRL enrichment pipeline, cutting deal-attribute extraction from hours to sub-minute output while standardizing 10+ fields.
  • Replaced ad-hoc research requests with a self-service dashboard, giving the team a persistent intelligence layer.
Jan – May 2026
New York, NY

AI Graduate Consultant

United Nations

Office of Legal Affairs · with Fordham

  • Delivered UN-LEX as a production tool adopted by the UN Office of Legal Affairs as its primary research interface across 9,000+ UNDT/UNAT cases spanning 15+ years of precedent.
  • Reduced case-law research time from hours to minutes — on-demand precedent lookup by fact pattern or misconduct type, with paragraph-level citations, delivered inside Microsoft Teams.
  • Captured senior officers' precedent expertise into a durable, queryable system — cutting onboarding time and mitigating operational risk from attorney turnover.
2023 – 2025
San Antonio, TX

Internship · Tutoring · Public sector

Earlier roles

  • Lead Tutor, First Generation Investors — led a team of four tutors delivering weekly personal-finance sessions (stocks, bonds, diversification, dollar-cost averaging) at two San Antonio high schools; guided students through a capstone where each invested $100 of real money.
  • Municipal Intern, Bexar County — documented weekly court proceedings under Judge Melissa Saenz (arraignments, bench trials, sentencing), researched local/state/federal statutes, and discussed case law and judicial reasoning directly with the judge.
  • Procurement Analyst Intern, Security Service FCU — managed contracts, POs, assets, and vendor records in System Center Service Manager, and ran IT device lifecycle: imaging, deployment, and secure decommissioning of PCs, laptops, and phones.

Stack

What I build with
Languages
Python TypeScript JavaScript SQL
AI / LLMs
Claude GPT-4o Ollama Azure OpenAI LangChain RAG Agents MCP Prompt Engineering LLM Evaluation
Web / Infra
Next.js React FastAPI Node.js Tailwind Vercel Railway
Data
Pinecone SQLite ChromaDB Azure AI Search Pydantic XBRL / SEC
Tools
Claude Code Cursor Codex Git Figma VS Code