Senior AI Engineer

Company Overview:

Global Technology Services is a rapidly expanding organization situated in Medellín, Colombia. We pride ourselves on possessing one of the most influential networks within software development and IT services for the entertainment, financial, and logistics sectors. Our corporate projections offer a multitude of opportunities for professionals to elevate their careers and experience substantial growth. Joining our team means engaging with expansive engineering teams across Latin America, Philippines and the United States, contributing to cutting-edge developments in multiple industries.

Currently, we are seeking a Senior AI Engineer with a strong English level to join our team. Here are the challenges that our next warrior will face and the requirements we look for: 

Position Title: Senior AI Engineer

Location: LATAM

What you will be doing:

BBG is building a data warehouse to consolidate property and appraisal data into a structured, queryable foundation. The goal is to allow BBG’s team and products to query this information through natural language and receive answers they can trust.

BBG currently uses Claude for appraiser-facing questions, but the model can hallucinate when answering domain-specific appraisal questions because it is not grounded in the company’s data. As an AI Engineer, your primary focus will be building the intelligent interface over the data warehouse so answers are accurate and traceable to trusted data.

This is a hands-on, applied role focused on modern LLM engineering, including retrieval, grounding, evaluation, and connecting language models to live data sources.

Key Responsibilities

• Build and own the interface between the LLM and BBG’s data warehouse, enabling natural-language and structured querying of appraisal data.

• Design and implement RAG and retrieval pipelines that ground model responses in warehouse data.

• Diagnose and reduce hallucinations through improved retrieval, prompt engineering, guardrails, and output validation.

• Build evaluation processes and test sets, ideally with input from BBG’s appraisers, to measure answer accuracy and identify regressions.

• Develop a query layer that translates user questions into safe and accurate warehouse queries, including validated natural-language-to-SQL.

• Collaborate with appraisers and domain experts to incorporate appraisal terminology, logic, and standards into prompts, retrieval processes, and evaluation criteria.

• Monitor model performance in production and improve quality, latency, and cost.

Required Skills & Experience

• 3–5 years of software engineering or machine-learning engineering experience, including recent hands-on work with LLM-powered applications.

• Practical experience building RAG or retrieval-augmented systems, including embeddings, vector search, chunking, and grounding strategies.

• Strong understanding of why LLMs hallucinate and proven techniques for reducing hallucinations through grounding, prompt design, guardrails, structured outputs, and evaluation.

• Solid machine-learning fundamentals, including an understanding of how models are trained and evaluated.

• Experience working with an Azure-based data warehouse, such as Microsoft Fabric, Azure Synapse, Azure SQL, or Databricks on Azure.

• Strong SQL skills, including the ability to write efficient queries.

• Hands-on experience with the Azure AI and data ecosystem, such as Azure OpenAI Service, Azure AI Search, vector search, and deploying services on Azure.

• Proficiency in Python and/or C#/.NET, with experience building APIs or backend services.

• Experience integrating LLM APIs into production systems, with familiarity using Claude, Azure OpenAI, or open-source language models.

• Ability to build evaluations and assess whether model responses are accurate and supported by the available data.

Nice to Have Skills

• Experience working in a regulated or domain-heavy field where accuracy is important, such as real estate, finance, insurance, legal, or healthcare.

• Familiarity with real estate appraisal or valuation concepts, including comparable properties, adjustments, USPAP, and market analysis.

• Experience fine-tuning open-source models and understanding when fine-tuning is or is not appropriate.

• Familiarity with natural-language-to-SQL techniques and their potential failure modes.

• Experience with orchestration or tooling frameworks such as LangChain, LlamaIndex, DSPy, or equivalent tools.

• MLOps or observability experience for LLM systems, including tracing, monitoring, and cost control.

Soft Skills

• Strong attention to accuracy and correctness.

• Ability to collaborate with appraisers and other domain experts.

• Analytical approach to evaluating model responses and identifying problems.

• Clear communication with technical and nontechnical stakeholders.

• Practical, hands-on approach to improving production AI solutions.

• Ability to consider quality, latency, and cost when evaluating model performance.

Why you will love GTS:

• Join a powerful tech workforce and help us change the world through technology

• Professional development opportunities with international customers

• Collaborative work environment

• Career path and mentorship programs that will lead to new levels.

Join GTS and contribute to shaping the data landscape within a dynamic and growing organization. Your skills will be honed, and your contributions will play a vital role in our continued success. GTS is an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees.