AI/ML Engineer

CVS

Location: Scottsdale, AZ (Hybrid 3 days a week from day 1)

Length of contract : 1 year (and will be renewed after that)

Rate: $65-67/hr C2C

About the Role

We are seeking an experienced AIML Engineer to design, build, and operate AI/ML infrastructure and agentic systems. This role involves developing MCP servers and agents, integrating LLMs, and implementing RAG pipelines for production environments.

Key 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.

Core Responsibilities

· 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.

Required Skills & Experience

· 5+ years of Strong Software Engineering (Python/NodeJS), system design and production service experience.

· 2+ years of Experience with LLMs, prompt engineering, and agent frameworks.

· 2+ years of Experience Practical experience implementing RAG: embeddings, vector DBs and retrieval tuning.

· 2+ years of Experience with LangChain patterns and with toolchain telemetry (Langfuse or similar) for prompt/model traceability.

· 5+ years of Experience with Kubernetes, Docker, CI/CD and infrastructure‑as‑code experience.

· 2+ years of Experience with Practical experience with Google Cloud Platform services

· 2+ years of Experience with Observability, testing, and security best practices for distributed systems.

· 2+ years of Experience with evaluating and mitigating retrieval/augmentation failures, hallucinations, and leakage risks in RAG systems.

· Familiarity with vendor and open‑source vector stores and embedding providers.

· Familiarity with CI/CD pipelines (Jenkins, GitHub Actions, GitLab CI, or ArgoCD).