MCP Solutions Architect

Sightly Enterprises
New York, NY, United States
2 months ago
Apply on indeed.com
Prepare application

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Compensation
$175,000.0
Working hours
Regular working hours
Job source

Tech stack

Application Programming Interfaces (APIs) Artificial Intelligence Software Debugging Python (Programming Language) Next.js SQL Databases Systems Integration Cloud Platform System Large Language Models Snowflake Backend Fastapi
+2 more
Automation Anywhere Docker

Job description

Sightly is building the cultural intelligence layer for modern media buying, and MCP is becoming a key way clients connect their AI agents, workflows, and internal tools directly to Brand Mentality’s data and intelligence. As our MCP Solutions Architect, you will help agencies, brands, and partners understand how Sightly’s MCP fits into their AI ecosystem. You’ll translate client use cases into clear agentic workflows, support technical onboarding, and work closely with Product, AI Engineering, and Data teams to improve our MCP tools and integrations. This is a technical, client-facing role. You should be comfortable talking to AI engineers, product leaders, and media strategists, while also being technical enough to test tools, read logs, understand schemas, and help debug issues.

What you’ll work on:

  • Help clients understand how to use Sightly’s MCP in their AI workflows
  • Translate client needs into clear MCP use cases and agent workflows
  • Support demos, pilots, onboarding, and technical discovery
  • Work with Product and Engineering to define new MCP tools and improvements
  • Troubleshoot tool call issues, integration problems, and unexpected agent behavior
  • Create documentation, examples, and best practices for clients
  • Act as the bridge between client technical teams and Sightly’s internal teams

Requirements

Do you have experience in Tooling?, * Strong understanding of MCP and how it differs from a traditional API

  • Hands-on experience with Claude, OpenAI, or similar LLM platforms
  • Familiarity with AI agents, tool calling, prompts, context windows, and structured outputs
  • Ability to understand tool schemas, parameters, logs, and common integration issues
  • Comfortable reading Python or backend code well enough to trace issues
  • Strong communication skills with both technical and non-technical audiences
  • Ability to turn vague client requests into clear workflows and implementation steps

Nice to have:

  • Experience building or integrating MCP servers
  • Experience with LangChain, LangGraph, Vercel AI SDK, CrewAI, or similar frameworks
  • Familiarity with FastAPI, FastMCP, SQL, Snowflake, vector databases, or embeddings
  • Experience with Docker, auth, secrets, cloud environments, or log-based debugging
  • Experience in media, adtech, social listening, or marketing intelligence

About the company

Sightly is a growing technology company leading the revolution in real-time marketing and brand intelligence. Join us as we pursue our disruptive mission to empower businesses everywhere to make the most authentic + profitable decisions in real time. Our AI-driven Brand Mentality® platform enables brands and agencies to leverage an ever-changing ocean of news, premium publisher, CTV, social, creator, and audience data to make more intelligent decisions at the speed of culture. At Sightly, we’re passionate about our product, our customers, our impact on the world, and most importantly our team.

Apply for this position

This job is hosted externally. Click below to view the full posting and apply.

Apply on indeed.com
Prepare application

Good distractions

Talks and stories from around this role — technically off-topic, practically not.

3:41 min

Integrating MCP servers for legacy tool connectivity

Sergio Freire Sergio Freire · Europe 2026 Virtual

2:07 min

Inspecting default bridge architectures and custom Docker networks

Oliver Seitz Oliver Seitz · World Congress 2025

4:30 min

Scaffolding pages and routing single-page applications with Next.js

Josh Goldberg · JS Congress

1:52 min

Structuring and scaling the backend engineering team

Stefan Lingler Stefan Lingler +1 · Coffee With Developers

2:21 min

Integrating Model Context Protocol for non-technical users

Jordan Tigani Jordan Tigani · World Congress 2026 Europe

2:34 min

Docker sandbox architecture and microVM environment integration

Manuel de la Peña Manuel de la Peña · World Congress 2026 Europe

Videos

See all

Related articles

See all