AI/ML Infrastructure Engineer: RAG & Agentic (Hybrid)

Steneral Consulting

Scottsdale (AZ)

Hybrid

USD 140,000 - 190,000

Full time

14 days+

Get more replies from employers

Send a job-specific resume in minutes.

Job summary

Steneral Consulting is seeking an experienced AI/ML Engineer to design, build and operate AI/ML infrastructure and agentic systems. You will design MCP servers/agents, integrate LLMs and implement RAG pipelines for production use.

The role emphasizes prompt engineering, toolchain telemetry, and scalable deployments on Kubernetes/Docker with Google Cloud. Collaboration across teams is required for reliable, cost-efficient AI workloads.

Qualifications

5+ years of strong software engineering (Python/NodeJS) and production services.
2+ years of experience with LLMs, prompts and agent frameworks.
2+ years implementing RAG with embeddings and vector databases.
2+ years using LangChain patterns and toolchain telemetry for tracing.
5+ years Kubernetes, Docker, CI/CD and infrastructure-as-code.
2+ years Google Cloud Platform services experience.
2+ years observability, testing, security for distributed systems.
Knowledge of 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 (Retrieval Augmented Generation) 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 code, APIs, and SDKs for model access and agent 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 (self hosted and cloud APIs) with unified adapters and telemetry.
Build developer tooling: CLI, local runner, simulators, and debugging tools for agents and prompts.
Containerize services (Docker), manage orchestration (Kubernetes/GKE), and optimize nodes, autoscaling and resource requests.
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, re ranking and context injection.
Integrate and instrument LangChain for composable chains, agents and tooling; use Langfuse (or equivalent tracing) to capture prompts, model calls, RAG traces and evaluation telemetry.