> Markdown version of [/jobs/ext/567011-ai-engineer](https://www.wearedevelopers.com/jobs/ext/567011-ai-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # AI Engineer - **Company:** Sightly Enterprises - **Location:** New York, NY, United States (Remote available) - **Salary:** $200,000.0 - **Contract:** Permanent contract - **Skills:** Multitier Architecture, Artificial Intelligence, Acceptance Test-Driven Development, Cloud Engineering, Software Debugging, Data Intelligence, Python (Programming Language), PostgreSQL, Automation of Marketing, Mockito, SQLAlchemy, TypeScript, ReactJS, Large Language Models, Multi-Agent Systems, Backend, Fastapi, Pytest, Gitlab-ci, Solid Principles, Real Time Data, Front End Software Development, Docker - **Published:** June 5, 2026 - **Apply:** https://www.indeed.com/viewjob?jk=17dc442b6e31405d ## About the Role Do you have experience in Workflow management (operations management method)?, + Experience building production agents, with real tool use, state management, and failure handling + Familiarity with at least one agent framework (Agno, LangGraph, CrewAI, or similar) + Strong understanding of multi-step reasoning, tool chaining, and when to use which pattern + Ability to write and iterate on system prompts that produce consistent, structured, schema-conformant outputs + Good judgment on when to use an agent vs. a deterministic workflow vs. a single LLM call * MCP & Tool Development + Hands-on experience building or consuming MCP servers (Model Context Protocol) + Understanding of tool schema design including parameter validation, error contracts, and what makes a tool LLM-friendly vs. brittle + Comfortable debugging tool call failures from the model side (hallucinated parameters, invalid combinations, timeout patterns) * LLM Proficiency + Deep familiarity with at least one frontier model family + Understanding of context windows, prompt caching, extended thinking, and cost/latency tradeoffs + Practical understanding of model behavior: failure modes, sampling temperature, structured output reliability * Evals & Quality + Experience designing evals for non-deterministic systems: regression suites, LLM-as-judge, golden datasets + Comfort instrumenting agents with tracing (Langfuse, LangSmith, or similar) and using traces to diagnose silent failures + Knows the difference between "the prompt works on my machine" and "the agent is production-ready" * Backend & Infrastructure + Python, FastAPI, FastMCP, async/await patterns + PostgreSQL, SQLAlchemy, Alembic + GCP (Cloud Run, Cloud SQL, GCS, Secret Manager) or equivalent cloud-native experience + Docker, CI/CD pipelines (GitLab CI a plus) * Software Engineering Fundamentals + Clean architecture habits, SOLID principles + Strong typing discipline (Pydantic models, type annotations) + Test-driven mindset: pytest, mocking external dependencies, covering edge cases not just happy paths Nice to have: * Experience with Temporal or other workflow orchestration tools * TypeScript / React familiarity (our frontend is React 19 + assistant-ui) * Media, adtech, or data intelligence domain knowledge * Experience designing agent outputs that feed into programmatic or social media buying workflows ## Description We're building the cultural intelligence layer for modern media buying and AI is at the center of how we deliver it. As our AI Engineer, you'll own the agent and MCP infrastructure that powers real-time data tools used by strategists, media planners, across media agencies and brands. This is a hands-on engineering role. You'll design and ship agents, extend our MCP server toolset, and work closely with product and data teams to turn raw cultural signals across news and social media into media intelligence and media activation. What you'll work on: * Agentic systems that orchestrate multi-step, non-deterministic workflows end-to-end: durable, observable, and reliable in production * MCP infrastructure with new tools, long-running background capabilities, and interactive surfaces that bring our intelligence directly into client agent environments * Data-to-activation pipeline that turns large-scale cultural and media signals into intelligence strategists and planners can act on * Integration of major media and advertising platforms to move seamlessly from insight to execution to measurement * Harden production agent infrastructure: evals, tracing, prompt and model management, cost controls, and guardrails for systems where outputs are probabilistic * Work across a Python, FastAPI, FastMCP, Temporal, PostgreSQL, and GCP stack, partnering closely with product, data, and design to shape how AI shows up for our users ## Related Videos - [On a Secret Mission: Developing AI Agents](https://www.wearedevelopers.com/videos/1510-on-a-secret-mission-developing-ai-agents) - [Intro to FastAPI](https://www.wearedevelopers.com/videos/462-intro-to-fastapi) - [pytest: Simple, rapid and fun testing with Python](https://www.wearedevelopers.com/videos/213-pytest-simple-rapid-and-fun-testing-with-python) - [Docker Compose: Rediscovered](https://www.wearedevelopers.com/videos/1978-docker-compose-rediscovered) - [Building and Deploying Multi-Agent Systems with ADK and Vertex AI](https://www.wearedevelopers.com/videos/1918-building-and-deploying-multi-agent-systems-with-adk-and-vertex-ai) - [Beyond Chatbots: How to build Agentic AI systems](https://www.wearedevelopers.com/videos/1629-beyond-chatbots-how-to-build-agentic-ai-systems) ## Related Articles - [Graph and AI Trends 2026: Why Is AI Running but Not Yet Delivering?](https://www.wearedevelopers.com/magazine/680-graph-and-ai-trends-2026-why-is-ai-running-but-not-yet-delivering) - [From Prototype to Production: Build AI Agents with This Free 4-Course Learning Path](https://www.wearedevelopers.com/magazine/655-from-prototype-to-production-build-ai-agents-with-this-free-4-course-learning-path) - [What is Agentic Programming and Why Should Developers Care?](https://www.wearedevelopers.com/magazine/625-what-is-agentic-programming-and-why-should-developers-care) - [Everything a Developer Needs to Know About MCP with Neo4j](https://www.wearedevelopers.com/magazine/604-everything-a-developer-needs-to-know-about-mcp-with-neo4j) - [Never delegate the understanding](https://www.wearedevelopers.com/magazine/749-never-delegate-the-understanding) - [A 5-Step Open-Source Setup for Agentic Engineering](https://www.wearedevelopers.com/magazine/738-a-5-step-open-source-setup-for-agentic-engineering)