Applied AI Engineer

Location: Manhattan, NY



Work Arrangement: Onsite



Duration: 6 Months + Contract-to-Hire



Experience: 6+ Years Job Summary

STAFFXPERT LLC is seeking an Applied AI Engineer on behalf of our client in Manhattan, NY . The ideal candidate will have strong software engineering fundamentals and hands-on experience building and deploying LLM-powered applications, AI workflows, and agent-based systems in production environments.

This role sits at the intersection of AI engineering, software development, data science, and customer engagement. The engineer will collaborate with Product, Engineering, Data Science, UX, Security, and business stakeholders to develop scalable AI-powered solutions and help teams adopt modern AI engineering practices.

• Build and iterate on AI-powered applications and workflows using LLMs, RAG, tool calling, and agent-based patterns.

• Develop scalable orchestration layers for prompting, retrieval, context management, and tool integration.

• Apply prompt engineering and multi-step workflow techniques to production AI applications.

• Work with frameworks and technologies such as LangChain, LangGraph, LlamaIndex, MCP/A2A, OpenAI SDKs, Google ADK, and Anthropic APIs .

• Design and implement cloud-native AI application architectures.

• Develop scalable production services and APIs using Python .

• Support AI engineering enablement by helping development teams integrate AI and ML capabilities into existing products.

• Contribute to reusable AI engineering standards, tooling, and best practices.

• Develop evaluation, monitoring, and observability capabilities for AI applications.

• Collaborate with data scientists, ML engineers, product managers, designers, and business subject-matter experts.

• Translate customer and business challenges into clear technical solutions and AI-powered workflows.

• Create technical documentation, sample applications, tutorials, and implementation guides.

• Participate in experimentation, testing, optimization, and production support for LLM-based applications.

• 6+ years of experience as a Software Engineer, AI Engineer, Platform Engineer, or related technical role.

• Strong production experience building and deploying LLM-powered applications .

• Strong Python programming skills and experience developing scalable production services and APIs.

• Experience designing AI application architectures in cloud-native environments.

• Hands-on experience with modern AI engineering frameworks such as LangChain, LangGraph, LlamaIndex, OpenAI APIs, Anthropic APIs, MCP , or equivalent technologies.

• Experience building AI workflows involving retrieval, tool calling, orchestration, context management, and structured generation .

• Experience deploying AI systems on AWS, Azure, or GCP .

• Familiarity with AI evaluation, observability, monitoring, and production reliability.

• Strong understanding of software engineering principles and production system development.

• Excellent communication and collaboration skills.

• Ability to work effectively with technical and non-technical stakeholders in an evolving environment.

• Experience with AI copilots, AI assistants, workflow automation, or multi-agent systems .

• Experience in legal technology, enterprise SaaS, compliance, financial services, healthcare, or other regulated industries.

• Experience with developer platforms, SDK development, API productization, or AI platform engineering.

• Experience facilitating technical workshops, hackathons, or developer enablement programs.

• Understanding of AI UX and conversational workflow design .

• Experience with AI evaluation, guardrails, policy enforcement, and responsible AI deployment.

• Familiarity with LLM inference optimization, serving infrastructure, or AI infrastructure tooling.

• Full-stack or frontend development experience for rapid AI prototyping.