Applied AI Scientist: Agentic Systems & Forecasting

XPO; Boston (MA); On-site; USD 100,000 - 120,000; Full time

Benefits offered by this job

Health insurance

Life and disability insurance

PTO 15 days

9 paid holidays

401(k) with company match

Education assistance

Incentive plan

Job summary

XPO is seeking an Applied AI Scientist in Boston to design agentic experimentation layers, build robust evaluation harnesses, and implement safeguards for autonomous systems. The role emphasizes collaboration with OR scientists, and deploying modern LLM-based architectures for ETA and demand forecasting.

Ideal candidates bring hands-on AI system building experience, strong Python skills, and a proven ability to explain AI tradeoffs to both technical and business stakeholders.

Qualifications

• Bachelor's degree or equivalent related work or military experience
• 1 year of experience designing evaluation harnesses or benchmarks to rigorously assess model or agent performance against existing baselines
• Hands-on experience building applied AI systems, including agent-based/agentic systems, experimentation frameworks, or applying LLM-based/foundation model architectures to time-series forecasting problems
• Proficiency in Python and modern ML/AI frameworks and platforms (e.g. PyTorch, HuggingFace)
• Strong communication skills, with the ability to explain AI system behavior and tradeoffs to technical and business stakeholders, and to collaborate closely with optimization/OR scientists on what constitutes a meaningful model improvement

Responsibilities

• Design and build agentic experimentation layer over optimization models, proposing variants and surfacing results
• Build evaluation harnesses to benchmark model and agent performance against baselines before production
• Implement operational safeguards for autonomous experimentation systems
• Evaluate and integrate modern LLM-based and foundation model architectures for ETA prediction and demand forecasting
• Partner with OR scientists to understand model internals and meaningful improvements for P&D use cases
• Collaborate with ML engineers on infrastructure for automated experimentation and evaluation at scale
• Communicate technical approaches to technical and business audiences
• Stay current on agentic systems and applied GenAI to guide adoption at XPO

Skills

Python

ML frameworks

PyTorch

HuggingFace

Communication skills

Cross-functional collaboration

Time-series forecasting

Education

Bachelor's degree

Master's or PhD in CS/AI/ML

Tools

PyTorch

HuggingFace

Chronos

Job description

XPO is seeking an Applied AI Scientist in Boston to design agentic experimentation layers, build robust evaluation harnesses, and implement safeguards for autonomous systems. The role emphasizes collaboration with OR scientists, and deploying modern LLM-based architectures for ETA and demand forecasting.

Ideal candidates bring hands-on AI system building experience, strong Python skills, and a proven ability to explain AI tradeoffs to both technical and business stakeholders.