AI/ML Engineer – RAG, LLMs & Kubernetes (Hybrid)

Tech Mirrors; Phoenix (AZ); Hybrid; USD 63,000 - 87,000; Full time

Job summary

Tech Mirrors is seeking an experienced AI/ML Engineer to design, build, and operate AI/ML infrastructure and agentic systems in a hybrid Phoenix environment. You will develop MCP servers and agents, integrate LLMs, and implement RAG pipelines for production workloads.

The role requires strong software engineering with Python/NodeJS, plus hands-on experience with Kubernetes, Docker, and cloud deployments. Excellent tooling, observability, and cost management are expected in this contract role.

Qualifications

• 5+ years of strong software engineering experience (Python/NodeJS)
• 2+ years with LLMs, prompt engineering, and agent frameworks
• 2+ years with RAG: embeddings, vector DBs, retrieval tuning
• 2+ years with LangChain patterns and observability tooling (Langfuse) for traceability
• 5+ years with Kubernetes, Docker, CI/CD and IaC
• 2+ years with Google Cloud Platform services
• 2+ years with observability, testing, and security in distributed systems
• 2+ years with mitigating retrieval/augmentation failures and hallucinations in RAG systems
• Familiarity with vendor and open-source vector stores and embedding providers

Responsibilities

• Design, build and operate MCP servers and MCP agents that host, orchestrate and monitor AI/agent workloads.
• Develop agentic AI, prompt engineering patterns, LLM integrations and developer tooling for production use.
• Own deployment, scaling, reliability and cost-efficiency on Kubernetes/Docker and Google Cloud with automated CI/CD.
• Design and implement RAG pipelines and integrations with vector stores and retrieval tooling; use LangChain and Langfuse for orchestration, chaining, and observability.
• Implement and maintain MCP server and agent APIs, SDKs for model access and orchestration.
• Design agent behavior, workflows and safety guards for agentic AI systems.
• Create, test and iterate prompt templates, evaluation harnesses and grounding/chain of thought strategies.
• Integrate LLMs and model providers with unified adapters and telemetry.
• Build developer tooling: CLI, local runner, simulators, and debugging tools for agents and prompts.
• Containerize services (Docker), orchestrate (Kubernetes/GKE), and optimize resources and autoscaling.
• Ensure observability: logging, metrics, traces, dashboards, alerting and SLOs for model infra and agents.
• Create runbooks, playbooks and incident response procedures; reduce MTTR and perform postmortems.
• Design and maintain RAG workflows: document chunking, embeddings, vector indexing, retrieval strategies and re-ranking.
• Integrate Lang Chain for composable chains, agents and tooling; use Langfuse to capture prompts and model calls.

Skills

Python

NodeJS

System design

Kubernetes

Docker

CI/CD

Google Cloud

Observability

LangChain

Langfuse

Vector stores

Embeddings

Tools

LangChain

Langfuse

Vector stores

Embeddings

Job description

Tech Mirrors is seeking an experienced AI/ML Engineer to design, build, and operate AI/ML infrastructure and agentic systems in a hybrid Phoenix environment. You will develop MCP servers and agents, integrate LLMs, and implement RAG pipelines for production workloads.

The role requires strong software engineering with Python/NodeJS, plus hands-on experience with Kubernetes, Docker, and cloud deployments. Excellent tooling, observability, and cost management are expected in this contract role.