Production AI Engineer: LLMs & Agentic Systems

OpenKrill; United States; Remote; USD 180,000 - 240,000; Full time

Benefits offered by this job

Health care for you and family

Unlimited PTO

Paid parental leave (14 weeks)

Professional development

401K / equity incentives

Mental health benefits

Equity incentives

Job summary

Red Cell Partners is seeking a Staff Applied ML Engineer for Red Cell Federal to build and deploy production AI systems for federal and national security missions in Washington, DC. You’ll work on LLMs, model fine-tuning, RAG, and agentic workflows to turn evolving AI capabilities into reliable software for real missions.

You’ll collaborate with Forward Deployed and Software Engineers, occasionally with customers, to understand operational problems and translate requirements into usable AI

Qualifications

• Significant experience building ML or AI systems and deploying in production.
• Hands-on experience with modern LLMs and foundation models.
• Deep expertise in several areas: LLM fine-tuning, model adaptation, evaluation, and retrieval.

Responsibilities

• Build production LLM-powered applications, AI agents, and agentic workflows.
• Develop and own model evaluation, fine-tuning, adaptation, and experimentation pipelines.
• Determine when to use prompting, RAG, fine-tuning, specialized models, or combinations of these approaches.
• Build rigorous eval systems for model and agent quality, reliability, tool use, and task completion.
• Develop retrieval and context systems across structured and unstructured mission data.
• Optimize models and inference for production environments.
• Deploy and improve models based on real-world performance and user feedback.
• Partner with engineers and customers to translate mission requirements into production AI capabilities.

Skills

Production ML systems

LLMs & foundation models

Model evaluation

RAG / retrieval

Agentic systems

Model serving

Embeddings retrieval

Job description

Red Cell Partners is seeking a Staff Applied ML Engineer for Red Cell Federal to build and deploy production AI systems for federal and national security missions in Washington, DC. You’ll work on LLMs, model fine-tuning, RAG, and agentic workflows to turn evolving AI capabilities into reliable software for real missions.

You’ll collaborate with Forward Deployed and Software Engineers, occasionally with customers, to understand operational problems and translate requirements into usable AI