AI Engineer

radixexperienced; Chicago (IL); On-site; USD 140,000 - 230,000; Full time

Job summary

radixexperienced is seeking a Quantitative Technologist to enhance live trading systems, research infrastructure, and alpha generation through technology innovation. You will build production-grade AI and ML platforms, and accelerate automation across data prep, modeling, and deployment.

The role requires strong Python, 5+ years of experience, and hands-on AI/LLM production work with LangChain and related tools.

Qualifications

• 5+ years of overall technical experience.
• 2+ years designing and building Generative AI/LLM applications in production.
• Bachelor's, Master's, or PhD in Computer Science, Data Science, Machine Learning, or related field.

Responsibilities

• Build and accelerate the firmwide AI ecosystem and infrastructure to support AI-native systems and tooling.
• Identify workflow opportunities for developers and researchers to introduce AI-first systems and automation.
• Design, deploy, and evaluate production-grade AI applications and advanced agentic workflows (utilizing RAG, semantic search, planning, and structured outputs).
• Develop platform-level safeguards, including bespoke evaluation harnesses, guardrails, approval workflows, tool-use limits, source attribution, and kill switches.
• Optimize core metrics across agent systems, focusing on reasoning quality, retrieval accuracy, latency, cost, safety, and user experience.

Skills

Python proficiency

AI lifecycle understanding

Prompt engineering

Software engineering

LangChain knowledge

Education

CS/DS/ML degree

Tools

LangChain

LangGraph

AutoGen

LlamaIndex

Job description

As a Quantitative Technologist, your goal is to enhance live trading systems, research infrastructure, and alpha generation through technology innovation.

We leverage cutting-edge software and hardware (mostly with modern C++) to push production level code daily and evolve fully-automated strategies, alpha generation processes, live trading systems, and machine learning research and simulation infrastructure used to analyze petabytes of data.

The Role

• Build and accelerate the firmwide AI ecosystem and infrastructure to support AI-native systems and tooling
• Identify workflow opportunities for developers and researchers to introduce AI-first systems and automation
• Design, deploy, and evaluate production-grade AI applications and advanced agentic workflows (utilizing RAG, semantic search, planning, and structured outputs)
• Develop platform-level safeguards, including bespoke evaluation harnesses, guardrails, approval workflows, tool-use limits, source attribution, and kill switches
• Optimize core metrics across agent systems, focusing on reasoning quality, retrieval accuracy, latency, cost, safety, and user experience

About You

• 5+ years of overall technical experience, including 2+ years of hands-on experience designing and building Generative AI/LLM applications in production
• Bachelor's, Master's, or PhD in Computer Science, Data Science, Machine Learning, or a related technical field
• Strong proficiency in Python alongside solid software engineering principles and a deep understanding of the full AI/ML lifecycle (data prep through observability)
• Expert familiarity with agentic frameworks and modern AI orchestration and development tools (e.g., LangChain, LangGraph, AutoGen, LlamaIndex) alongside deep practical skills in prompt engineering
• Proven capability to evaluate and select foundational or open-weight models, balancing enterprise trade-offs across capability, context length, hosting, security, and cost

COMPENSATION - Competitive base salary, plus quarterly bonus based on individual performance and contribution towards success of others and the firm.