Photon Logo

Photon

Senior MCP / Agentic AI Specialist | Onshore

Posted 4 Days Ago
Remote
Hiring Remotely in United States
120K-420K Annually
Senior level
Remote
Hiring Remotely in United States
120K-420K Annually
Senior level
Design, build, integrate, and secure production MCP servers, clients, connectors, and agentic AI workflows. Develop tool integrations with external systems, implement OAuth and least-privilege authorization, and contain rogue-agent risks through sandboxing, policy controls, egress restrictions, and human approvals. Operate reliable, observable, cost-efficient infrastructure across cloud and Kubernetes environments. Create evaluation systems, maintain MCP registries, support multi-agent interoperability, and provide technical leadership in a rapidly evolving AI platform domain.
The summary above was generated by AI

Senior MCP / Agentic AI Specialist 

Department: Agentic AI & Platform Engineering · Level: Senior / Staff 

We are looking for a Senior MCP / Agentic AI Specialist to design, build, and secure the Model Context Protocol (MCP) infrastructure that connects large language models to the tools, data, and systems they need to act autonomously. MCP has become the de facto open standard for giving models structured access to the outside world, and it now underpins connectors and app ecosystems across Claude, ChatGPT, Cursor, and a growing universe of agent hosts. You will be the go-to expert for how agents discover, call, and safely use tools at production scale — from authoring servers and clients against the raw JSON-RPC protocol to shipping hardened connectors that real users and real agents depend on. 

Your role is central: you will own the MCP servers, clients, and tool-integration layers that let AI agents reliably retrieve context and take action, while defending against a fast-evolving threat landscape — tool poisoning, rug pulls, prompt injection through tool outputs, confused-deputy token abuse, and malicious or misbehaving agents. You will balance capability with containment, giving the business powerful agentic automation without handing autonomous systems more trust, access, or blast radius than they have earned. 

Key Responsibilities 

MCP Server & Client Development: Build production MCP servers and clients from scratch that correctly implement the specification — JSON-RPC 2.0 messaging, capability negotiation, and the full set of primitives (Tools, Resources, Prompts, and the client-side Sampling, Roots, and Elicitation features). Design clean tool schemas with strict input/output validation and keep pace with an actively evolving spec. 

Transports & Protocol Fluency: Implement and operate both standard transports — stdio for local servers and Streamable HTTP for remote ones — and manage the migration away from the deprecated standalone HTTP+SSE transport while maintaining backwards compatibility where older clients require it. 

Host & Connector Integration: Wire MCP servers into real hosts: Claude (Claude Desktop extensions and remote custom connectors), ChatGPT (connectors and the Apps SDK, including tool-rendered widgets), Cursor, and other MCP clients. Understand each host's connection model, authentication flow, and transport support so connectors behave correctly across web, desktop, and mobile surfaces. 

External System Connectors: Expose databases, SaaS APIs, and internal services as well-designed MCP tools and resources. Handle authentication, pagination, rate limits, retries, and error recovery so tools behave predictably under load, and turn repetitive integration work into reusable connector patterns. 

MCP Security: Defend the tool layer against the attacks unique to this ecosystem — tool poisoning (malicious instructions hidden in tool descriptions, schemas, or outputs), rug pulls (tool definitions mutated after approval), tool shadowing / cross-origin escalation, prompt injection via tool results, and data exfiltration through legitimate channels. Treat all tool metadata and responses as untrusted input, pin and hash complete tool definitions, integrate MCP scanning into CI, and vet third-party and untrusted servers for supply-chain risk. 

Authorization & Secrets: Implement OAuth 2.1 (with PKCE and Resource Indicators) for remote MCP servers so tokens are audience-bound to the intended server, validated on every request, and never passed through to upstream APIs. Close confused-deputy gaps by separating server execution identity from caller authorization, enforce least-privilege scopes, and store credentials in secure, short-lived, rotation-friendly form. 

Rogue-Agent Containment: Design guardrails and controls that keep autonomous and multi-agent systems safe when they misbehave — sandboxing and isolation of MCP servers, least-privilege and deny-by-default tool permissions, egress allowlisting to limit exfiltration, human-in-the-loop approvals for sensitive actions, and kill-switches to halt runaway agents. Build contextual, flow-based policy checks that block unsafe data paths and unauthorized tool invocations. 

Agentic Orchestration & Interop: Build and optimize single-agent and multi-agent workflows using frameworks such as LangGraph, AutoGen, CrewAI, LlamaIndex, and the OpenAI and Anthropic agent SDKs. Enable reliable tool calling, planning, and memory, and implement agent-to-agent (A2A) coordination — Agent Cards, task delegation, and secure inter-agent messaging — alongside MCP tool access. 

Discovery & Distribution: Publish, discover, and manage MCP servers through the official MCP registry and private sub-registries, standardize server.json-style metadata, pin versions and image digests, and maintain an approved-server catalog that blocks ad hoc installation of unreviewed servers. 

Reliability, Observability & Cost: Make the MCP layer production-grade with health checks, timeouts, retry policies, circuit breakers, tracing, metrics, and graceful degradation under concurrency. Optimize token, context, and cost to maximize answer quality per dollar. 

Evaluation & Quality: Build evaluation harnesses, test datasets, and benchmarks that measure agent accuracy, tool-call reliability, latency, and cost, and catch regressions in both tool behavior and safety before they reach production. 

Technical Leadership: Set best practices for building and securing agents and tools, mentor engineers, and shape the standards other teams build on in a fast-moving, still-maturing domain. 

Required Qualifications 

  • 6+ years in software engineering, backend/distributed systems, or ML/platform engineering, including hands-on work on production GenAI or agentic systems. 
  • Demonstrated, hands-on experience with the Model Context Protocol — building MCP servers and clients, designing tool schemas, and working across transports (stdio, Streamable HTTP, legacy SSE) and primitives (Tools, Resources, Prompts, Sampling, Roots, Elicitation). 
  • Experience integrating MCP into real hosts and connectors (Claude connectors/Desktop, ChatGPT connectors/Apps SDK, Cursor, or similar) and exposing external systems as tools. 
  • Strong grasp of MCP and LLM/agent security: tool poisoning, rug pulls, prompt injection, confused-deputy/OAuth token issues, and supply-chain risk, plus the controls to mitigate them. 
  • Hands-on with OAuth 2.1 / OIDC (PKCE, resource indicators, audience validation), secrets management, and least-privilege access design. 
  • Experience building LLM-powered applications: function/tool calling, prompt design, RAG, and context/token management. 
  • Familiarity with at least one agent framework (LangGraph, AutoGen, CrewAI, LlamaIndex, OpenAI Agents SDK, or Anthropic agent SDK). 
  • Strong API and integration skills: REST, JSON-RPC 2.0, WebSockets/SSE, and robust error handling. 
  • Expert in Python and/or TypeScript; proficiency in Go or Rust is a plus. 
  • Experience deploying and operating services on cloud (AWS, GCP, or Azure) with containers/Kubernetes and solid observability. 

Preferred Qualifications 

  • Contributions to open-source MCP SDKs, the MCP registry, agent frameworks, or MCP security tooling. 
  • Experience building agent guardrails, sandboxing, egress controls, or human-in-the-loop approval systems for autonomous agents. 
  • Familiarity with the A2A (Agent2Agent) protocol and multi-agent interoperability patterns. 
  • Experience publishing or operating remote MCP servers consumed by third-party hosts at scale. 
  • Familiarity with evaluation tooling (e.g., Ragas, LangSmith) and with optimizing token cost and latency for high-volume LLM workloads. 
  • Working knowledge of OWASP guidance for LLM/agentic applications and current MCP security research. 
  • Comfort operating with autonomy in a fast-moving, evolving domain. 

Compensation, Benefits and Duration

Minimum Compensation: USD 120,000
Maximum Compensation: USD 420,000
Compensation is based on actual experience and qualifications of the candidate. The above is a reasonable and a good faith estimate for the role.
Medical, vision, and dental benefits, 401k retirement plan, variable pay/incentives, paid time off, and paid holidays are available for full time employees.
This position is available for independent contractors
No applications will be considered if received more than 120 days after the date of this post.

Photon New York, New York, USA Office

New York, United States

Similar Jobs

6 Hours Ago
Remote
USA
Entry level
Entry level
Artificial Intelligence • Hardware • Productivity • Robotics • Software • Automation • Manufacturing
Deploy robotics solutions at customer manufacturing sites by defining ambiguous problems, integrating software, hardware, sensors, and manufacturing processes, and delivering measurable production results. The role includes robot programming and debugging, system architecture, customer collaboration, operator adoption, commissioning, rapid prototyping, and contributing site-specific solutions back to the broader platform. Travel to customer sites is approximately 50% of the time.
Top Skills: 3D ModelingAi ToolsCadComputer VisionGazeboIndustrial Communication ProtocolsIsaacManufacturing DrawingsMatlabMetrology ToolsMicrocontrollersMoveitOmniversePlcsPrompt EngineeringRoboticsRosRos-IndustrialRvizVendor Motion Apis
10 Hours Ago
Remote or Hybrid
Mid level
Mid level
Cloud • Fintech • Software • Business Intelligence • Consulting • Financial Services
Develops and implements consultative and technical IT solutions for clients. Responsibilities include level-three escalation support, Microsoft and cloud environment assessments, security reviews, technology roadmaps, risk and modernization recommendations, project scoping and budgeting, and client communication. The role requires coordinating technical resolutions, managing multiple projects, and traveling approximately 15% to client locations in Pennsylvania.
Top Skills: Active DirectoryAntivirusAzure Active DirectoryCloud ApplicationsEndpoint DevicesFirewallsLocal NetworksMicrosoft 365AzureServersSharepointSwitchesVirtualized Environments
10 Hours Ago
Remote or Hybrid
Senior level
Senior level
Cloud • Fintech • Software • Business Intelligence • Consulting • Financial Services
Manage and review complex tax returns and consulting for partnership clients, leading client service teams while training and mentoring staff, ensuring excellent client relationships and compliance with tax regulations.
Top Skills: Tax-Related Software

What you need to know about the NYC Tech Scene

As the undisputed financial capital of the world, New York City is an epicenter of startup funding activity. The city has a thriving fintech scene and is a major player in verticals ranging from AI to biotech, cybersecurity and digital media. It also has universities like NYU, Columbia and Cornell Tech attracting students and researchers from across the globe, providing the ecosystem with a constant influx of world-class talent. And its East Coast location and three international airports make it a perfect spot for European companies establishing a foothold in the United States.

Key Facts About NYC Tech

  • Number of Tech Workers: 549,200; 6% of overall workforce (2024 CompTIA survey)
  • Major Tech Employers: Capgemini, Bloomberg, IBM, Spotify
  • Key Industries: Artificial intelligence, Fintech
  • Funding Landscape: $25.5 billion in venture capital funding in 2024 (Pitchbook)
  • Notable Investors: Greycroft, Thrive Capital, Union Square Ventures, FirstMark Capital, Tiger Global Management, Tribeca Venture Partners, Insight Partners, Two Sigma Ventures
  • Research Centers and Universities: Columbia University, New York University, Fordham University, CUNY, AI Now Institute, Flatiron Institute, C.N. Yang Institute for Theoretical Physics, NASA Space Radiation Laboratory

Sign up now Access later

Create Free Account

Please log in or sign up to report this job.

Create Free Account