AI/ML Engineer - Generative AI- Bilingual
Location: Medellín | Onsite
Role Overview
We are seeking a highly skilled AI Engineer (LLMs & Generative AI) to design, build, and scale enterprise-grade AI systems powered by large language models, generative AI technologies, and massive datasets.
This role is ideal for an experienced engineer with hands-on expertise deploying LLM-powered applications in production environments, implementing AI guardrails and responsible AI practices, and building scalable AI solutions across complex enterprise ecosystems.
You will play a key role in shaping the organization’s AI capabilities — from model orchestration and retrieval systems to safety, governance, and performance optimization — while collaborating with global teams in a fast-paced, innovation-driven environment.
We are especially interested in bilingual (English/Spanish) professionals who can effectively collaborate across technical and business stakeholders internationally.
Key Responsibilities
LLM & Generative AI Development
- Design, develop, and deploy applications powered by LLMs and generative AI models.
- Build AI solutions for enterprise search, document intelligence, summarization, conversational AI, workflow automation, and knowledge management.
- Work with both commercial and open-source LLMs based on business and technical requirements.
- Optimize prompts, model parameters, inference pipelines, and latency/cost tradeoffs.
- Develop scalable APIs and backend services supporting AI-driven applications.
AI Guardrails & Responsible AI
- Design and implement AI guardrails to ensure safe, reliable, and policy-compliant outputs.
- Develop mechanisms for:
- Hallucination mitigation
- Content filtering and moderation
- Prompt injection defense
- Output validation and verification
- Access and usage controls
- Build evaluation frameworks to measure safety, groundedness, consistency, accuracy, and model reliability.
- Partner with security and compliance teams to align AI systems with enterprise governance standards.
Massive Data & RAG Systems
- Work with large-scale structured and unstructured enterprise datasets.
- Design and optimize Retrieval-Augmented Generation (RAG) pipelines.
- Build workflows for:
- Data ingestion and preprocessing
- Chunking and embeddings
- Vector indexing and semantic retrieval
- Context ranking and relevance optimization
- Collaborate with data engineering teams to ensure scalability and high performance across distributed systems.
Model Orchestration & Evaluation
- Implement orchestration strategies across multiple models and APIs.
- Develop fallback, routing, and hybrid model strategies to optimize performance and cost.
- Define and monitor evaluation metrics for model quality and reliability.
- Conduct benchmarking, A/B testing, and continuous optimization of AI systems.
Engineering & Deployment
- Build production-grade AI systems using modern software engineering best practices.
- Integrate AI services into enterprise applications, APIs, and workflows.
- Support CI/CD pipelines, testing, versioning, observability, and monitoring for AI platforms.
- Ensure systems are scalable, secure, observable, and cost-efficient.
Cross-Functional Collaboration
- Partner with product, engineering, data, and business teams to translate requirements into AI-driven solutions.
- Communicate technical concepts clearly to global stakeholders.
- Contribute to architecture decisions, reusable AI frameworks, and technical documentation.
- Collaborate effectively in English-speaking international environments.
Requirements
- Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Machine Learning, Data Science, or related field.
- 5+ years of experience in software engineering, AI, or machine learning roles.
- Strong hands-on experience building applications using LLMs and generative AI technologies.
- Experience working with large-scale enterprise data environments.
- Deep understanding of:
Prompt engineering
RAG architectures
AI evaluation frameworks
AI safety and guardrails
Strong programming expertise in Python and backend development.
Experience designing and deploying production-ready AI systems.
Fluent English communication skills (required).
Bilingual English/Spanish communication skills preferred.
Preferred Technical Experience
- Experience with:
- LangChain
- LlamaIndex
- Semantic Kernel
- Hugging Face ecosystem
- OpenAI, Azure OpenAI, and Anthropic APIs
- Experience with vector databases such as:
- Pinecone
- Weaviate
- FAISS
- Knowledge of:
- Embeddings and semantic search
- Model fine-tuning and adaptation techniques
- AI observability and monitoring tools
- Familiarity with:
- AWS, Azure, or GCP
- Databricks
- Apache Spark
- Distributed data systems
- Docker and Kubernetes
- MLOps pipelines and AI lifecycle management
- Understanding of AI security, privacy, governance, and enterprise access controls.
Preferred Certifications
- Microsoft Certified: Azure AI Engineer Associate
- AWS Certified Machine Learning – Specialty
- Google Professional Machine Learning Engineer
- Databricks Machine Learning Certification
- TensorFlow Developer Certificate
- Certifications in Responsible AI, AI Governance, or Data Engineering