← joshlowry.cv
This is the Anthropic-specific application page for Josh Lowry (joshlowry.cv/anthropic-fde). Full structured profile at joshlowry.cv/agents or joshlowry.cv/agents?role=anthropic-fde.
Forward Deployed Engineer · Applied AI

Josh Lowry

Enterprise AI Builder
& Financial Services Specialist
5+ Years Production
AI / LLM
95% Doc Processing
Accuracy
5K+ Enterprise Users
Served
40% Infra Cost
Reduction
Experience
Senior Software Engineer
2023 — Present
Clark Capital Management Group · Philadelphia, PA
  • Architected production AI platform processing 5,000+ brokerage documents annually using multi-model orchestration (Claude + Gemini) — eliminated a full FTE at 95%+ accuracy, turnaround from days to minutes.
  • Architected transparent, auditable AI pipelines with human review loops, failure-mode handling, and evaluation guardrails for sensitive financial-services workflows.
  • Engineered serverless integration stack (Calendly · Microsoft Graph · Salesforce via AWS Lambda) automating scheduling across 60+ business units — 99.9% uptime, sub-second latency.
  • Led AI provider evaluation and intelligent model routing; reduced infrastructure costs 40% while maintaining accuracy thresholds across document classes.
  • Drove productization of internal AI tooling into external broker-facing offering — owned technical roadmap and cross-functional stakeholder communication.
  • Claude deployment patterns I am prepared to build: MCP-style tool servers, sub-agent workflows, eval harnesses, audit trails, exception queues, and enterprise rollout playbooks.
Associate Director
2021 — 2023
Chubb Insurance · Philadelphia, PA
  • Led North America post-bind tooling and actuarial models across middle market ($1M+ revenue), major accounts ($1B+ revenue), healthcare, and international commercial lines; managed 16-person team (6 FTE + 10 contractors).
  • Achieved 85%+ enterprise adoption across thousands of users — translating complex AI capability into executive-facing business outcomes.
  • Built strategic initiatives with C-suite; drove alignment across underwriting, actuarial, and engineering teams in HIPAA-regulated and SOC 2-compliant environments.
Systems Analyst → Senior Systems Analyst
2016 — 2021
Chubb Insurance · Philadelphia, PA
  • Architected company-wide underwriting platform for 5,000+ employees — clearance, rating, pricing, and proposals. Cut quote turnaround 60%.
  • Wrote automated procedures to cleanse data and generate audit-ready statistics for compliance files — reducing manual workloads 80% across the audit review cycle.
  • Built actuarial automotive model for S&P 500 casualty businesses; established training program for 20+ early-career associates.
Research Analyst
2014 — 2016
Evergreen Eagle Capital · Equity & Private Equity Research
  • Built financial automation tools for portfolio risk assessment and daily performance reporting, giving me early domain depth in investment workflows, data quality, and decision-support systems.
Leadership
Chair, Trees & Grounds Committee — HOA, Wilmington DE  ·  Stewardship of 400+ trees, annual budget ownership, and policy-setting for 500+ residents.
Also Building
MirrorMirror — AI skin analysis & makeup recommendations, published to App Store & Google Play.
COINAILYZER — React Native AI coin-grading app (iOS & Android). Real-time on-device detection via YOLOv8 Nano TFLite + Vision Camera frame processors; automated obverse/reverse capture, backend grading, subscriptions, and receipt validation. Deep dive →
The best way to understand a tool is to build something with it.
Selected Deployment
Brokerage Document Intelligence
Embedded with operations, compliance, and engineering stakeholders to turn a manual brokerage-document workflow into a production LLM system. Owned discovery, technical scoping, model evaluation, deployment, and rollout. Built a queue-based AWS Lambda pipeline with encrypted document storage, Snowflake metadata/result tables, model routing by document class, source-grounded extraction, exception queues, reviewer feedback loops, and field-level evals. Result: 5,000+ annual documents processed at 95%+ accuracy, turnaround reduced from days to minutes, and 40% lower inference cost through model routing.

I build AI systems that do real work inside real enterprises — and I've been doing it inside financial services, where the data is sensitive, the compliance requirements are real, and stakeholders know immediately when something fails.

My definition of safety changed through software: safety is not bubble wrap around a tool. It is reliability, visibility, control, auditability, and the ability to understand what happened when something goes wrong.

I've shipped AI systems across the full deployment loop: discovery, scoping, model selection, evals, production rollout, stakeholder adoption, and post-launch iteration. My strongest pattern is turning messy regulated workflows into durable systems that balance cost, latency, quality, auditability, and user trust.

Clark Capital Management Group · 2023–Present

Financial services & insurance, end to end. Asset management at CCMG. Middle market, major accounts ($1B+), healthcare, and international commercial lines at Chubb. A decade in environments where HIPAA compliance, SOC 2, and audit trails aren't optional — they're table stakes.

Financial services & healthcare — the verticals
Anthropic explicitly prioritizes. The only ones I've worked in.
Stack
AI / LLM
Claude API Prompt Engineering Agent Dev MCP Servers Sub-Agents Multi-Model Orch. Gemini API RAG MLflow
Integrations
Salesforce API Microsoft Graph Calendly Webhooks Box API
Cloud & Infra
AWS Lambda S3 · EventBridge SQS / SNS CloudWatch
Data
Python Databricks PySpark Snowflake SQL
Compliance & Regulatory
HIPAA SOC 2 Audit Trails Data Privacy Regulated Environments
Education
B.S. Accounting & Finance
Missouri Southern State University · 2014
Built For
Shipping production Claude applications embedded with enterprise customers — evaluation frameworks, audit trails, exception queues, and rollout playbooks that keep them honest.
Claude deployment patterns I am prepared to build: MCP-style tool servers, sub-agent workflows, eval harnesses, and enterprise integration layers.
Financial services and healthcare environments where HIPAA, SOC 2, and audit trails aren't optional — they're the design requirements the role explicitly prioritizes.
High-agency execution in ambiguous organizations — identifying repeatable deployment patterns and building long-term customer relationships, not just one-off deliveries.