AI Engineer (NLP)

We're looking for a Senior ML / AI Engineer to own and evolve our LLM-powered user experience. You'll work directly with our technical co-founder to build, optimize, and monitor agent systems that parse workout descriptions, provide scaling recommendations, and enable conversational data retrieval - all with production-grade accuracy and speed.

This is a hands-on role focused on the ML / AI engineering side : prompt engineering, model optimization, agent orchestration, and continuous improvement based on real-world usage patterns.

What You’ll Do

Core Responsibilities

Own the workout parsing system : improve accuracy of our fine-tuned model (currently Qwen-based) that converts natural language workout descriptions into structured schemas

Design and implement agent workflows for workout scaling recommendations and performance tracking

Build observability workflows using Langfuse to identify and systematically address model performance issues

Optimize agent response latency while maintaining accuracy across our tool-based reasoning system

Collaborate on agent architecture decisions, including potential migration to frameworks like DSPy

Ship production features : workout entry system, scaling recommendations, and score reporting

What We’re Looking For

Required

5+ years of ML / AI engineering experience with at least 2 years working with LLMs in production

Strong prompt engineering and model optimization skills

Experience building and deploying agent systems with tools / functions

Proven ability to use observability platforms to diagnose and improve model performance

Experience with model fine-tuning (any framework / approach)

Strong Python programming skills

Active CrossFit participant - candidates should understand standard movements and workout structures

Strongly Preferred :

Experience with agent orchestration frameworks (DSPy, LlamaIndex, or similar)

Background in production ML operations and monitoring

Experience with Modal.com or similar serverless ML platforms

Track record of iteratively improving LLM systems based on user feedback and metrics

Experience fine tuning similar open-source LLMs

Success in First 6 Months

Ship workout entry system with improved parsing accuracy

Launch basic workout scaling recommendations

Implement user score reporting and retrieval

Establish robust monitoring workflows to catch and address model failures and poor user experiences

Contribute to agent architecture decisions as we scale