Job ID: JOB_ID_2012
Position Summary
We are seeking a highly skilled and experienced AI/ML Engineer to join our team in Scottsdale, AZ. This is a contract position focused on designing, building, and operating cutting-edge AI/ML infrastructure and agentic systems. The ideal candidate will have a deep understanding of Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) pipelines, and modern cloud-native orchestration tools like Kubernetes and Docker. You will be responsible for the full lifecycle of AI workloads, from initial design to production monitoring and optimization.
Core Responsibilities
- Design, build, and operate MCP (Model Context Protocol) servers and agents to host, orchestrate, and monitor AI workloads.
- Develop agentic AI patterns, including prompt engineering, LLM integrations, and developer tooling for production environments.
- Implement and optimize RAG (Retrieval-Augmented Generation) pipelines, integrating with vector stores and retrieval tools.
- Utilize LangChain and Langfuse for orchestration, chaining, and observability of AI models and agentic workflows.
- Manage deployment, scaling, and reliability on Google Cloud Platform (GCP) using automated CI/CD pipelines.
- Containerize services using Docker and manage orchestration via Kubernetes (GKE), optimizing nodes and resource requests.
- Ensure system observability through logging, metrics, traces, and dashboards, maintaining high SLOs for model infrastructure.
- Create runbooks and incident response procedures to reduce MTTR and perform thorough post-mortems.
Technical Requirements
- 5+ years of strong software engineering experience using Python or NodeJS, with a focus on system design and production services.
- 2+ years of hands-on experience with LLMs, prompt engineering, and agent frameworks.
- 2+ years of practical experience implementing RAG, including document chunking, embeddings, and vector DB tuning.
- 2+ years of experience with LangChain patterns and toolchain telemetry (e.g., Langfuse) for prompt and model traceability.
- 5+ years of experience with Kubernetes, Docker, CI/CD, and Infrastructure as Code (IaC).
- 2+ years of experience with Google Cloud Platform (GCP) services and cloud-native architecture.
- Proven ability to mitigate retrieval/augmentation failures, hallucinations, and leakage risks in RAG systems.
Preferred Skills
- Familiarity with open-source vector stores and embedding providers.
- Experience with CI/CD pipelines such as Jenkins, GitHub Actions, or ArgoCD.
- Strong understanding of security best practices for distributed systems and AI model access.
- Excellent problem-solving skills and the ability to work independently in a fast-paced, evolving technical landscape.
Special Requirements
Visa: US Citizen (ship: US). Local candidates only. Contract position.
Compensation & Location
Salary: $165,000 – $225,000 per year (Estimated)
Location: Scottsdale, AZ
Recruiter / Company – Contact Information
Recruiter / Employer: 3B Staffing LLC
Email: tu…@3bstaffing.com
Recruiter Notice:
To remove this job posting, please send an email from
tu…@3bstaffing.com with the subject:
DELETE_JOB_ID_2012