Senior AI Engineer
Remote
Job Summary
Design, develop, and ship agentic AI products on the platform, managing agent identities, reusable skills, and tool integrations via a config-driven architecture. Engineer system prompts, context injection from live data sources, and structured outputs using Pydantic schemas. Build agent tools that query Databricks, MongoDB, and external systems, integrating with the ecosystem through the Model Context Protocol. Operate services by instrumenting them with OpenTelemetry, monitoring reliability and cost in Grafana, and enforcing deterministic quality gates with LLM-as-judge evaluators. Collaborate with cross-functional teams to deliver end-to-end AI solutions while staying current with the agentic AI landscape. This is a PJ contract based in Brazil.
Required Qualifications
- Strong software engineering fundamentals in Python, including modern async Python
- Hands-on experience building LLM-powered applications in production: agents / tool use / function calling, prompt engineering, RAG, and structured outputs
- Experience with at least one major LLM provider API (OpenAI, Anthropic, Google)
- Experience with FastAPI (or an equivalent modern web framework) and Pydantic
- Understanding of how to evaluate AI systems: offline evals, LLM-as-judge, regression benchmarks, and quality metrics beyond 'it looks right'
- Familiarity with cloud platforms (we run on Azure — Container Apps, Key Vault, Container Registry) and containerized deployment with Docker
- Experience with databases in production (we use MongoDB and Databricks SQL warehouses)
- Solid testing habits (pytest or similar) and comfort with CI/CD pipelines
- Excellent problem-solving and analytical skills, and the autonomy expected of a senior engineer: you own a problem end to end — from framing to shipped, monitored outcome — and are accountable for the result, not just the merge
- Bachelor's degree or higher in Computer Science, Artificial Intelligence, or a related field — or equivalent practical experience
Desired Qualifications
- Experience with the Model Context Protocol (MCP) or similar agent-integration standards
- Experience with observability stacks: OpenTelemetry, Grafana, Loki, structured logging
- Experience with Databricks beyond SQL (Delta Sharing, jobs, model serving)
- Track record of shipping something from 0 to 1 in a fast-moving environment where priorities shift often
- Experience with classification pipelines and fine-tuning where they beat prompting
- Contributions to open-source AI tooling
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.