AI Engineer

Location: Remote across Argentina, the Dominican Republic, the United States, Mexico, Chile, and Colombia, aligned to the client's working day and United States time zones.

Salary: USD remuneration.

Company

hirify.global is a San Francisco-based software development company that builds and operates production AI systems and provides nearshore AI engineering teams.

What you will do

• Build retrieval systems with chunking and embedding pipelines, hybrid search, reranking, and retrieval-quality evaluation.
• Develop stateful agentic workflows with tool calling, MCP servers, structured outputs, context management, fallbacks, and human-in-the-loop controls.
• Design LLM evaluation suites with representative test sets, model-as-judge scoring, regression tracking, and error analysis.
• Implement prompt-injection defenses, output validation, guardrails, PII handling, and graceful degradation.
• Deploy and operate containerized AI systems on Azure or AWS with CI/CD, observability, and explicit latency, cost, and token budgets.
• Work in client repositories and delivery environments, including engagements with SOC 2 and HIPAA requirements.

Requirements

• 4+ years building and shipping production software, primarily with a modern backend language such as Python.
• Production experience with LLM-based systems, including retrieval-augmented generation, function and tool calling, structured outputs, and prompt design.
• Hands-on experience with vector and retrieval infrastructure such as pgvector, Pinecone, Qdrant, FAISS, or Azure AI Search.
• Experience shipping stateful, tool-using systems with LangGraph, LangChain, CrewAI, MCP, or native Python execution loops.
• Experience building an LLM evaluation suite with test-set design, scoring, and regression tracking is screened most heavily.
• Cloud deployment, Docker, CI/CD, infrastructure as code, AI-assisted coding tools, and clear written and spoken English at B2/C1 or above.

Nice to have

• Fine-tuning and adaptation of open-weight models with LoRA, QLoRA, or PEFT.
• Self-hosted inference, multimodal systems, streaming or high-throughput workloads, and LLM-specific security testing.
• Experience with SOC 2 or HIPAA compliance, open-source AI contributions, technical writing, or AI engineering communities.

Culture & Benefits

• Production AI engineering with vendor-neutral use of OpenAI, Anthropic, and open-weight models.
• AI-assisted development tools such as Claude Code, Codex, Cursor, and GitHub Copilot are part of the standard toolchain.
• Paid time off and United States holidays.
• AI training, certifications, and mentored career development.
• Profit sharing and USD remuneration.
• Time supported for open-source work, community teaching, and philanthropy.