Senior MCP & Agentic AI Specialist

McKinsol Consulting Inc

Dallas, TX • 10m ago • On-site

Senior

On-site

  1. Select offer
  2. Add resume
  3. Analyze
  4. Improve
  5. Apply
  6. Auto-send · soon

Match your resume with similar open roles

Upload your resume to automatically match with active openings similar to this role.

PDF up to 10 MB

Your resume is private & secure

Quick Facts

  • Role: Senior MCP & Agentic AI Specialist

Description

You will design, build, and secure Model Context Protocol (MCP) infrastructure that connects large language models to tools, data, and systems for autonomous action. You will own MCP servers/clients and tool-integration layers, integrating with major agent hosts and production-grade connectors. You will also build security, authorization, reliability, observability, and evaluation to defend against evolving agent and tool threats.

Responsibilities

  • Develop production MCP servers and clients implementing MCP specification primitives (Tools, Resources, Prompts, Sampling, Roots, Elicitation) and strict tool schema validation.
  • Implement and operate MCP transports including stdio and Streamable HTTP; migrate away from deprecated HTTP+SSE while maintaining backward compatibility.
  • Integrate MCP into hosts/connectors (Claude, ChatGPT, Cursor, and other MCP clients) including authentication flows.
  • Expose external systems (databases, SaaS APIs, internal services) via MCP tools/resources with pagination, rate limits, retries, and error recovery.
  • Apply MCP-specific security controls for tool poisoning, rug pulls, prompt injection via tool outputs, confused-deputy/OAuth issues, cross-origin escalation, and data exfiltration.
  • Implement secure authorization and secrets handling using OAuth 2.1 (PKCE, resource indicators, audience-bound tokens) with least-privilege scopes.
  • Create guardrails to contain rogue or misbehaving autonomous/multi-agent systems (sandboxing, deny-by-default permissions, egress allowlisting, human approvals, kill-switches).
  • Build and optimize agent workflows using agent frameworks, enabling reliable tool calling and agent-to-agent coordination.
  • Manage MCP discovery and distribution via official and private registries with version pinning and an approved-server catalog.
  • Ensure production reliability and cost efficiency with health checks, timeouts, retries, circuit breakers, tracing, metrics, and graceful degradation.
  • Build evaluation harnesses and benchmarks for accuracy, tool-call reliability, latency, cost, and safety.
  • Provide technical leadership: set standards, mentor engineers, and influence emerging practices in a fast-evolving domain.

Requirements

  • 6+ years software engineering with backend/distributed systems or ML/platform engineering, including hands-on work on production GenAI/agentic systems.
  • Hands-on experience with MCP: building servers/clients, designing tool schemas, and implementing across transports and primitives.
  • Experience integrating MCP into real hosts/connectors and exposing external systems as MCP tools/resources.
  • Strong MCP and LLM/agent security knowledge and mitigation practices.
  • Hands-on OAuth 2.1/OIDC (PKCE, resource indicators, audience validation), secrets management, and least-privilege design.
  • Experience building LLM-powered applications (tool calling, prompt design, RAG, context/token management).
  • Familiarity with at least one agent framework (LangGraph, AutoGen, CrewAI, LlamaIndex, OpenAI Agents SDK, Anthropic agent SDK).
  • Strong API/integration skills (REST, JSON-RPC 2.0, WebSockets/SSE) with robust error handling.
  • Expert in Python and/or TypeScript; Go or Rust is a plus.
  • Experience deploying/operating cloud services with containers/Kubernetes and observability.
  • Ability to build evaluation harnesses/test datasets/benchmarks for agent reliability, safety, latency, and cost.

Preferred Qualifications

  • Open-source contributions to MCP SDKs/registry or agent frameworks.
  • Experience building agent guardrails (sandboxing, egress controls, human-in-the-loop approvals).
  • Familiarity with A2A (Agent2Agent) interoperability patterns.
  • Experience operating remote MCP servers at scale.
  • Familiarity with evaluation tooling (e.g., Ragas, LangSmith) and optimizing token cost/latency.
  • Working knowledge of OWASP guidance for LLM/agentic applications and current MCP security research.

See similar jobs

Explore similar jobs and use your resume score to choose where to apply next

See more

Unlock Full Resume Report