AI Engineer (LLM / Python)

We are looking for people who are curious, collaborative, and excited to build reliable technology that supports a mission-driven healthcare platform. Be part of a great engineering team that constantly challenges its status quo to build the best product in the industry alongside our Product and DevOps teams.

Job Description

Looking for a Senior Software Engineer - AI to design, build, and operate LLM-powered product features and internal AI tooling that drive real business value for healthcare organizations. You will take AI capabilities from prototype to production, working with LLM APIs, retrieval-augmented generation (RAG), embeddings and vector databases, and agentic workflows, while making sure every solution is measurable, reliable, cost-efficient, secure, and HIPAA-aware. This role collaborates closely with Product, DevOps, and Data/IT teams, breaks down ambiguous problems into actionable tasks with minimal oversight, and helps establish AI engineering best practices, evaluation standards, and responsible AI guidelines across the organization.

Responsibilities

• Build AI Product Features: Design, develop, and ship LLM-powered features (assistants, intelligent search, summarization, content and document generation) into the MedTrainer platform, from prototype to production.
• RAG and Retrieval: Build and tune retrieval-augmented generation pipelines, including document ingestion, chunking, embeddings, vector search, re-ranking, and grounded answers with citations.
• Agents and Internal AI Tooling: Create agents, tool/function-calling workflows, and internal AI tools that automate processes and boost productivity across Engineering, Product, and operations.
• Evaluation and Quality: Own prompt engineering and evaluation by building eval datasets, automated and LLM-as-judge evals, and regression tests that gate releases and prove quality improvements.
• Production Engineering: Develop Python services and APIs that integrate with our existing platform (PHP/Node), deployed with Docker, Kubernetes, and GitHub Actions on Azure/AWS, with observability for quality, latency, and cost.
• Security, Privacy, and Responsible AI: Apply HIPAA-aware data handling, PHI/PII minimization and redaction, prompt-injection defenses, guardrails, and human-in-the-loop controls where needed.
• Collaboration and Culture: Partner with Product, DevOps, and Data/IT to define success metrics, communicate progress and trade-offs clearly, and share AI knowledge and best practices across the team.

Qualifications

• Education: Bachelor’s degree in Computer Science, an equivalent degree, or equivalent professional experience.
• Professional Experience: 4+ years of software engineering experience, including at least 1 year building and operating LLM/ML-powered features in production.
• Methodological Background: Proven experience working within structured Agile/Scrum development environments.
• Language Proficiency: Advanced English skills are considered a plus.

Essential Technologies and/or Skills

• LLMs and APIs: Hands-on experience with LLM APIs such as OpenAI, Anthropic, and/or Azure OpenAI, including structured outputs, streaming, and function/tool calling.
• RAG, Embeddings, and Vector Databases: Practical experience with embeddings, vector databases (pgvector, Pinecone, Qdrant, Azure AI Search, or similar), and retrieval strategies such as hybrid search and re-ranking.
• Prompt Engineering, Evals, and Agents: Strong prompt engineering skills, experience building evals, and familiarity with agent/orchestration frameworks (LangChain, LangGraph, LlamaIndex, Semantic Kernel, or equivalent).
• Backend and APIs: Strong Python skills (FastAPI or similar) and REST API design; familiarity with PHP (Symfony) or Node.js is a plus. Experience with Model Context Protocol (MCP) and AI-assisted development tools is a plus.
• Cloud, Containers, and CI/CD: Experience with Azure and/or AWS, Docker, Kubernetes, and CI/CD with GitHub Actions, plus observability of AI systems (tracing, logging, token and cost monitoring). Git, Jira, and Software Development Lifecycle best practices.
• Performance, Security, and Compliance: Cost and latency optimization of LLM workloads, security and privacy best practices, HIPAA-aware handling of sensitive data, and responsible AI principles. Healthcare or regulated-industry experience is a plus.

Additional Information

• Work Location: 100% remote work from anywhere within Mexico.
• Compensation: Competitive monthly salary (paid after taxes).
• Health and Wellness: Major Medical Insurance and healthcare coverage, along with wellness benefits such as TotalPass gym discounts.
• Home Office Support: Financial support for home office setup and ergonomics (including internet, electricity, and an office chair disccount).
• Growth and Development: Professional development opportunities, including company-provided English classes.
• Financial Benefits: Savings plan.
• Time Off: Paid time off, including personal days.
• Culture and Tech Stack: A collaborative, international, and growth-oriented environment with an engineering culture focused on automation, reliability, and continuous improvement. You will have the opportunity to work with modern cloud infrastructure, leading LLM platforms, and AI-assisted development tools.

All received information will be kept confidential according to EEO guidelines.