About this role
The candidate will lead the development of intelligent, AI-driven applications from concept through deployment, focusing on both frontend and backend architecture. Responsibilities include building scalable web applications, implementing distributed systems, and optimizing AI-enabled workflows involving task orchestration and automated recovery. The technical environment includes Next.js, JavaScript/TypeScript, Python, Node.js, and various LLM integrations like OpenAI and Anthropic. The role involves partnering with product, engineering, and machine learning teams to deliver business-critical features and continuously improve system performance through monitoring and observability. The engineer will work on projects involving multi-agent workflows, real-time interactions, and RAG solutions.
Skills & technologies
Must have
Nice to have
- Retrieval-Augmented Generation
- RAG
- Agentic AI
- Generative AI
- Open Source LLMs
Read full description
LHH Recruitment Solutions is seeking MULTIPLE Senior Full Stack AI Engineers in St. Louis, MO to lead the development of intelligent, AI-driven applications from concept through deployment. This role combines modern software engineering practices with advanced AI integration, requiring expertise across frontend development, backend architecture, agent-based workflows, and large language model (LLM) technologies.
Title: Full Stack AI Engineer
Type: Direct Hire/Permanent
Reason for opening: Company growth; adding to headcount
Compensation will vary depending on experience and is very broad due to multiple openings on the team.
This role offers both a base salary and bonus opportunities
Job Description:
- Develop scalable web applications and intelligent software solutions spanning frontend interfaces, backend services, and AI-powered capabilities.
- Architect and implement distributed systems, APIs, and service integrations that support high-performance, production-grade applications.
- Build and optimize AI-enabled workflows that incorporate planning, task orchestration, tool execution, exception handling, and automated recovery processes.
- Create responsive, real-time user experiences utilizing streaming responses, event-driven architectures, and low-latency interactions.
- Integrate large language models, contextual memory frameworks, and external services to deliver reliable and intelligent application behavior.
- Enhance application resiliency through monitoring, observability, fault tolerance, and performance optimization initiatives.
- Partner with product, engineering, and machine learning teams to deliver business-critical features from design through release.
- Evaluate production feedback and usage patterns to continuously improve system performance, usability, and AI effectiveness.
- Make sound engineering decisions while balancing technical excellence, business priorities, and evolving project requirements.
Required Qualifications
- Proven experience designing and delivering full stack applications across both frontend and backend environments.
- Strong background in software architecture, system design, and API development best practices.
- Demonstrated success leading product features through the complete software development lifecycle, from requirements through production release.
- Experience building AI-powered applications utilizing LLMs, contextual memory systems, and third-party integrations.
- Expertise designing multi-agent or orchestration-based workflows that support complex decision making and task execution.
- Experience developing applications that support real-time interactions, streaming data, and performance-sensitive workloads.
- Strong understanding of reliability engineering, monitoring, observability, and system recovery strategies.
- Ability to operate effectively in dynamic environments with evolving priorities and limited direction.
Preferred Qualifications
- Hands-on experience developing production applications using Next.js, Python, and/or Node.js.
- Experience building Retrieval-Augmented Generation (RAG) solutions, agentic AI systems, or generative AI applications.
- Knowledge of containerized and cloud-native technologies including Docker and Kubernetes.
- Experience designing and supporting both SQL and NoSQL database environments.
- Familiarity with AI frameworks such as PyTorch and integrations with OpenAI, Anthropic, or open-source language models.
- Experience developing reusable AI infrastructure components, including memory layers, model abstractions, and tool integration frameworks.
- Background establishing AI evaluation strategies, monitoring models in production, and improving workflow success rates through data-driven optimization.
Technical Environment
Frontend: Next.js, JavaScript/TypeScript
Backend: Python, Node.js
AI & Machine Learning: OpenAI, Anthropic, Open Source LLMs, PyTorch
Data Platforms: SQL, NoSQL Databases
Containerization & Orchestration: Docker, Kubernetes
APIs & Integrations: RESTful Services, AI Tooling, External Platform Integrations
