Open to opportunities

Jared Hoffen

@jaredhoffen

Message

I’m a Senior AI Engineer focused on production LLM agents and RAG systems.

United States

Message

What I'm looking for

I want to build reliable, low-latency LLM agent and RAG systems in production—paired with strong evaluation, observability, and cost optimization—where engineering quality and safety guardrails are valued.

I’m a Senior AI Engineer with 12+ years of experience building production-grade backend systems, machine learning infrastructure, and GenAI applications. I specialize in LLM agents, retrieval-augmented generation (RAG), and distributed AI systems, with a strong emphasis on evaluation, reliability, and production monitoring.

In my current contract role, I’ve designed and deployed LLM agent systems that support multi-step reasoning and tool execution across production workflows, including multi-agent orchestration and dynamic context routing (improving task success rate by ~20–30%). I’ve implemented scalable RAG pipelines, built evaluation frameworks (LLM-as-a-judge) that reduced regression detection time by ~40%, and optimized inference cost/latency through caching and batching (reducing token usage by ~25–35%), while adding safety guardrails such as prompt injection mitigation and output validation. Previously at Airbnb, HubSpot, and DigitalOcean, I delivered ranking/recommendation and NLP systems, event-driven data pipelines, and robust observability—using monitoring, drift detection, retries, and idempotency patterns to improve reliability and incident response.

Experience

Work history, roles, and key accomplishments

Current

Senior AI Engineer

Current

AI Research Lab

Jan 2024 - Present (2 years 5 months)

Designed and deployed production LLM agent systems with tool execution, multi-agent orchestration, and dynamic context routing, improving task success rate by ~20–30%. Built RAG pipelines and evaluation frameworks and reduced regression detection time by ~40%, while optimizing prompt/caching/batching to reduce token usage by ~25–35% with added safety guardrails and observability.

Multi agent orchestration LLM Evaluation Prompt Injection Mitigation Tool Function Calling Vector Databases Observability

Machine Learning Engineer

Airbnb

Jan 2019 - Dec 2023 (4 years 11 months)

Built ranking and recommendation systems for marketplace personalization and developed large-scale NLP pipelines for classification and tagging. Implemented A/B testing and real-time/batch inference pipelines, alongside monitoring for drift, performance tracking, and regression detection.

Recommendation Systems A B Testing Feature Engineering Model Monitoring Monitoring For Drift

Software Engineer II

Hubspot

Jul 2016 - Dec 2018 (2 years 5 months)

Built event-driven data pipelines and backend services supporting ML workflows, experimentation systems, and product telemetry/analytics. Improved observability to reduce debugging and incident resolution time, and increased pipeline reliability using retries, idempotency, and backfill strategies.

Data Pipelines Python Observability MongoDB

Backend Engineer

Digitalocean

Jul 2013 - May 2016 (2 years 10 months)

Developed Node.js REST API services for developer platform workflows including authentication, rate limiting, and multi-tenant backend operations. Designed and optimized PostgreSQL schemas and improved performance using Redis caching, supporting AWS-based deployments and early infrastructure.

REST APIs API Rate Limiting PostgreSQL Redis API Design