
Senior AI Engineer
Posted Aug 25

Posted Aug 25
This is a fully remote position, open to applicants in Mexico.
• Lead the architecture and technical evolution of an application platform and artificial intelligence agents.
• Define and maintain the technical architecture of the platform and its services.
• Design LLM-agnostic abstractions including routing, fallback, budgets, and uniform observability.
• Determine which tasks should be addressed with models and which should be handled through code, compilers, schemas, or deterministic workflows.
• Design reliable, bounded, auditable agents capable of operating with external tools.
• Evolve the MCP integration, capability catalog, and execution gateways.
• Design secure models for identity, consent, credentials, permissions, quotas, and revocation.
• Ensure idempotence, traceability, isolation, and proper handling of retries and partial failures.
• Create reproducible pipelines for building, verification, deployment, and rollback with immutable artifacts.
• Develop evaluation suites and end-to-end tests for prompts, models, tools, security, and runtime.
• Define security standards for generated code, dependencies, containers, networking, and supply chain.
• Investigate end-to-end incidents and correct structural root causes.
• Design SLOs, metrics, alerts, and operational dashboards.
• Lead architecture and code reviews, document decisions, and provide technical support to the team.
• Evaluate models, frameworks, and vendors through evidence, benchmarks, and total cost analysis.
• Strong experience with Python, FastAPI, Pydantic, SQLAlchemy, and Alembic.
• Experience with React, TypeScript, REST APIs, and modern web applications.
• Proficiency in PostgreSQL, data modeling, indexing, migrations, and query optimization.
• Experience building products with LLMs, tool calling, structured outputs, RAG, agents, and context management.
• Knowledge of multi-provider architectures for Anthropic, OpenAI, or other model providers.
• Experience designing distributed, asynchronous, event-driven, and idempotent systems.
• Knowledge of OAuth 2.1, OIDC, PKCE, SCIM, RBAC/ABAC, and secure secret management.
• Practical experience with GCP: Cloud Run, Cloud SQL, Secret Manager, Artifact Registry, Cloud Build, Pub/Sub, Cloud Tasks, IAM, and IAP.
• Experience with Docker, CI/CD, observability, distributed tracing, and incident response.
• Ability to design versioned contracts, stable APIs, and clear service boundaries.
• Experience defining evaluations, quality metrics, costs, latency, and regressions for AI systems.
• Technical English proficiency and the ability to clearly communicate architectural decisions.
• Nice to have: experience as a Platform Engineer.
• Nice to have: experience implementing remote MCP servers and clients.
• Nice to have: knowledge of compilers, intermediate representations, application graphs, or schema-based generation.
• Nice to have: experience with BigQuery and scheduled data workloads.
• Nice to have: experience with sandboxes for executing untrusted code and egress policies.
• Nice to have: knowledge of OpenTelemetry, LLM tracing, and human-calibrated automatic evaluation.
• Nice to have: experience with distroless containers, SBOM, image signing, and attestations.
• Nice to have: experience in low-code/no-code platforms, developer platforms, or internal tooling.
• Nice to have: experience in FinTech or systems with high security and auditing requirements.
• Work culture based on trust and purpose.
• Environment that values creativity and curiosity.
• Space to contribute ideas and feedback.
• Culture of belonging and inclusion.
• Transparency in communication and decision-making.
• Work focused on real impact.
brightfin
TRM Labs
Thumbtack
Thumbtack
Get handpicked remote jobs straight to your inbox weekly.