Artificial Intelligence Engineer

🇨🇴 🇲🇽 Exclusive to candidates based in Colombia and Mexico

Requirements

Must-haves

• 3+ years of software or data engineering experience
• Experience building AI features in production software: LLM integrations, AI agents, RAG, agentic workflows
• Experience with Python
• Experience with Snowflake
• Experience with SQL, PostgreSQL
• Experience building data pipelines and ETL processes
• Experience working with datasets and data processing
• Experience shipping AI features into existing products, not only greenfield projects
• Experience with RESTful APIs and back-end concepts sufficient to prototype, test, and evaluate integrations
• Ability to retrieve and store data safely through a back-end
• Deep knowledge of core computer science topics (e.g., optimization, algorithms, etc.)
• Strong communication skills in both spoken and written English

Nice-to-haves

• Startup experience
• Experience with LLM APIs and foundation model providers (e.g., OpenAI, Claude, etc.)
• Experience with agentic workflows and AI agent frameworks (e.g., LangChain, etc.)
• Experience with Databricks
• Experience with RAG and vector databases (e.g., Pinecone, Weaviate, etc.)
• Experience with computer vision or AI image recognition, including at a prototyping level
• Experience with cloud services, particularly AWS (e.g., S3, Lambda, etc.)
• Proficiency with prompt engineering
• Exposure to civil engineering, transportation infrastructure, or geospatial data to critically evaluate AI outputs in these domains and communicate credibly with domain experts
• Bachelor's Degree in Computer Engineering, Computer Science, or equivalent

What you will work on

• Build AI features into our existing products, creating AI workflows that improve automation across data extraction and processing
• Own the application of AI to QA/QC processes, setting strategy and iterating with the Data team to strengthen data quality and integrity
• Integrate LLMs and AI agents into production software, applying tool use and other techniques to get the most out of the models
• Work with the Data team on datasets for evaluation, in-context learning (ICL), and related applications
• Act as the domain bridge between civil/transportation engineering knowledge and AI capabilities, judging whether model outputs meet real-world infrastructure standards
• Direct AI image recognition and computer vision approaches for infrastructure asset data extraction, validating outputs against domain benchmarks
• Assess third-party AI tools, APIs, and foundation models against our use cases, weighing build vs. buy tradeoffs with Engineering
• Partner with the Research team on prompting techniques, model capabilities, and domain adaptation
• Prototype concepts and turn technical findings into actionable product decisions
• Collaborate with the Engineering, Data, and Research teams to build repeatable processes