Agentic AI Research Engineer - Planning & Decision Support

Code Metal, Inc.; Boston, Northern (MA, KY); Hybrid; USD 150,000 - 230,000; Full time

Benefits offered by this job

Health care plan

401k with matching

Paid Time Off

Flexible hybrid or remote work

Relocation assistance

Job summary

Code Metal, Inc. is advancing AI systems for defense planning, wargaming, and decision-support. This Applied AI Research Engineer role focuses on human-machine teaming, agentic AI, and integration with simulation and planning software to enable faster, more explainable and trustworthy operational workflows.

You will work with researchers and engineers to turn research ideas into production-ready capabilities, including multi-agent workflows and robust tool use for planning and adjudication.

Qualifications

• Bachelor’s or Master’s degree in related technical field or equivalent practical experience.
• 3+ years building AI or applied research systems.
• Strong Python engineering skills.
• Experience with PyTorch and modern LLM tooling (Transformers, vLLM, Hugging Face, etc.).
• Experience building or deploying agentic AI systems and multi-step reasoning pipelines.
• Experience fine-tuning, evaluating, or serving language models.
• Experience with embeddings, vector search, or knowledge retrieval systems.
• Strong experiment design, benchmarking, and model evaluation.
• Ability to move quickly from research prototype to production-quality implementation.
• Eligible to obtain a U.S. security clearance.

Responsibilities

• Design and build agentic AI systems for planning, decision support, and human-machine teaming.
• Develop AI pipelines that integrate foundation models, retrieval, simulation, external tools, and deterministic software.
• Design, run, and analyze experiments to evaluate model and agent performance, reliability, traceability, latency, cost, and user trust.
• Fine-tune, distill, and evaluate foundation models for domain-specific planning and decision-support tasks.
• Build datasets, retrieval pipelines, automated benchmarks, and experiment infrastructure for continuous model improvement.
• Partner with software engineers to transition research prototypes into scalable AI services.
• Collaborate with domain experts to ensure AI outputs remain explainable and under human control.

Skills

Python engineering

PyTorch

LLM tooling

Agentic AI systems

Retrieval-augmented generation

Embeddings

Vector search

Experiment design

Production deployment

Security clearance

Education

Bachelor’s or Master’s degree in CS/ML/Engineering/Math/Physics

Tools

PyTorch

Transformers

vLLM

Hugging Face

Retrieval tooling

Job description

Code Metal, Inc. is advancing AI systems for defense planning, wargaming, and decision-support. This Applied AI Research Engineer role focuses on human-machine teaming, agentic AI, and integration with simulation and planning software to enable faster, more explainable and trustworthy operational workflows.

You will work with researchers and engineers to turn research ideas into production-ready capabilities, including multi-agent workflows and robust tool use for planning and adjudication.