Senior AI Engineer (RAG & LLMs)

Join DaCodes!
We are a software and digital transformation firm delivering high-impact technology solutions.
For over 10 years, we’ve been creating innovation-driven products thanks to our team of 220+ talented #DaCoders, including developers, architects, UX/UI designers, PMs, QA testers, and more. Our team collaborates on projects with clients across LATAM and the U.S., consistently achieving outstanding results.
At DaCodes, you’ll have the opportunity to accelerate your professional growth, work across diverse industries, and contribute to the design, implementation, and optimization of cloud-based infrastructures.
Our DaCoders have a huge impact on the success of both our business and our clients’. You’ll be the expert contributing to key projects while gaining exposure to disruptive startups and global brands.

Interested? Keep reading 👇

Requirements

Project Context

A global advisory company in the healthcare sector is developing a Retrieval-Augmented Generation (RAG) Application to build its own secure, enterprise-grade ChatGPT, ensuring data privacy, security, and traceability for its client organizations.
This role requires a technical and product-minded engineer, capable of designing scalable, secure, and production-ready SaaS architectures.

Desired Profile

• 4+ years of software development experience, including at least 2 years working with Generative AI or RAG-based systems.
• Strong command of Python and JavaScript/TypeScript, with hands-on experience in modern AI frameworks and integrations.
• Proven experience building RAG pipelines and managing vector databases (Pinecone, FAISS, Weaviate).
• Solid understanding of secure cloud architectures (AWS) and handling sensitive or regulated data.
• Experience with LLMs from both open-source and commercial ecosystems (OpenAI, Anthropic, Cohere, Mistral, etc.).
• Product-driven mindset — results-oriented, iterative, and focused on user experience.
• Intermediate to advanced English for technical communication and documentation.

Nice to Have

• Knowledge of healthcare compliance frameworks (HIPAA, GDPR, SOC2).
• Experience building enterprise AI copilots or chatbots.
• Familiarity with prompt engineering, evaluation frameworks (LangSmith, PromptLayer), and AI observability tools.

Key Responsibilities

• Design, develop, and implement a RAG-based AI Application for the healthcare sector, prioritizing data security, compliance, and privacy (HIPAA / SOC2-ready).
• Build and integrate RAG pipelines combining semantic search, embeddings, and LLMs for secure contextual responses.
• Develop agentic AI workflows using frameworks such as LangChain, LlamaIndex, Semantic Kernel, Auto-GPT, and BabyAGI.
• Integrate both open-source LLMs (LLaMA, Mistral, Falcon) and enterprise LLMs (OpenAI, Anthropic, Cohere), optimizing performance and cost.
• Configure and manage vector databases (Pinecone, FAISS, Weaviate) for efficient knowledge retrieval and storage.
• Deploy AI solutions on AWS (Lambda, S3, QuickSight, API Gateway) following security and scalability best practices.
• Design and integrate REST and GraphQL APIs, ensuring system interoperability and reliability.
• Collaborate with product, UX, and data science teams to transform prototypes into SaaS-ready MVPs, delivering seamless chat, voice, and dashboard experiences.

Benefits

🚀 Work with global brands and disruptive startups.

🏡 Remote / home office.

📍 If a hybrid or on-site modality is required, you’ll be informed from the first session.

⏳ Work schedule aligned to the assigned project team.

📅 Monday to Friday work week.

🎉 Birthday day off.

🏥 Major medical insurance (Mexico).

🛡️ Life insurance (Mexico).

🌎 Multicultural teams.

🎓 Access to training courses and certifications.

📢 Meetups with special guests from the IT industry.

📡 Virtual team-building events and interest groups.

📢 English classes.

🏆 Opportunities across our business lines.

🏅 Proudly certified as a Great Place to Work.