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.
About the role:
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
Core Competencies:
Agent Engineering
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
Location: This role is remote as we are a 100% distributed company