Junior AI/ML Engineer

Resolv Global; Toluca; Remoto; MXN 665.000 - 1.108.000; Tempo pieno

Descrizione del lavoro

Resolv Global is seeking Junior AI/ML Engineers to build AI agents for voice and chat customer conversations. You will work on retrieval, orchestration, APIs and integrations behind these systems, turning prototypes into reliable production solutions with security and practicality in mind.

You will collaborate with full-stack engineers, CX designers and operations teams to develop AI-powered experiences that are practical, secure and effective, leveraging Python, cloud platforms and LLM APIs to

Competenze

• 1–3 years of software/ML engineering experience.
• Solid Python skills; familiarity with Git, Docker and SQL.
• Experience with at least one cloud platform: Azure, AWS or Google Cloud.
• Hands-on with an LLM API (OpenAI, Anthropic, Gemini or Azure OpenAI).
• Experience building AI agents that call tools/APIs with a framework (LangChain/LangGraph/Semantic Kernel).
• Experience building a RAG pipeline with embeddings, vector search and retrieval tuning.
• Experience building REST APIs with authentication, rate limits and versioning.
• Experience connecting systems via webhooks, SDKs or message queues.
• English and Spanish proficiency; based in Colombia or Mexico.

Mansioni

• Build AI agents that interact with users, call tools and APIs, and hand off to humans when needed.
• Develop retrieval pipelines to answer questions using approved sources.
• Integrate agents with CRMs, ticketing systems, databases and messaging channels.
• Build and manage APIs with gateways, authentication and versioning.
• Support voice AI development with STT, LLMs and TTS in English and Spanish.
• Test and improve quality with evaluations, tests and guardrails.
• Support deployment and monitoring via CI/CD and documentation.
• Collaborate with engineering, CX design and operations to productionize prototypes.

Conoscenze

Python

Git

Docker

SQL

LLM APIs

RAG pipelines

REST APIs

Webhooks

English/Spanish

Strumenti

Azure

AWS

Google Cloud

LangChain

LangGraph

Semantic Kernel

Descrizione del lavoro

We are hiring Junior AI/ML Engineers to help build AI agents that handle customer conversations through voice and chat.

You'll work on the retrieval, orchestration, APIs, and integrations behind these systems, helping turn working prototypes into reliable production solutions. You'll collaborate with full-stack engineers, CX designers, and operations teams to develop AI-powered experiences that are practical, secure, and effective.

We welcome candidates with relevant professional experience, internships, research, or hands-on projects who are eager to develop their skills and contribute to real-world AI applications.

What You'll Do

• Build AI agents: Develop conversational agents that interact with users, call tools and APIs, and hand conversations off to human agents when needed.
• Develop retrieval pipelines: Build retrieval-augmented generation (RAG) pipelines that help AI agents answer questions using approved information sources.
• Integrate systems: Connect AI agents with CRMs, ticketing systems, databases, and messaging channels.
• Build and manage APIs: Work with API gateways, authentication, rate limits, and versioning.
• Support voice AI development: Help build voice agents using speech-to-text, large language models (LLMs), and text-to-speech in English and Spanish.
• Test and improve quality: Use evaluations, automated tests, and guardrails to improve accuracy, reliability, and safety.
• Support deployment and monitoring: Ship and maintain solutions through CI/CD, monitoring, and documentation.
• Collaborate across teams: Work with engineering, CX design, and operations colleagues to turn prototypes into production-ready solutions.

Our Technology Stack

Our primary cloud platform is Microsoft Azure, but experience with AWS or Google Cloud is also valuable.

Relevant technologies include Python, Git, Docker, SQL, LLM APIs, agent frameworks, RAG pipelines, REST APIs, API gateways, webhooks, messaging systems, and cloud-based AI services.

Experience with any one of the named tools in each relevant area is sufficient. You don't need to have used every framework or platform listed.

Working Environment

This is a fully remote opportunity for candidates based in Colombia or Mexico. You'll work with full-stack engineers, CX designers, and operations teams to build and improve AI-powered customer conversation solutions.

We value curiosity, practical problem-solving, collaboration, and a willingness to learn. You'll have the opportunity to contribute to AI agents, retrieval systems, integrations, and voice AI applications while developing your engineering skills.

Hiring Process

To ensure fairness and consistency, all applicants must complete every stage of the hiring process.

• Resume Review
• Pre-Screen Questionnaire
• One-Way Video Interview
• Live Interview

Please Note

• This is an English-speaking role that requires strong written and verbal English communication skills.
• All resumes must be submitted in English to be considered for this position.

Requirements:

What You'll Bring

• 1–3 years of experience in software engineering or ML engineering. Relevant internships and research experience count.
• Solid Python skills and familiarity with Git, Docker, and basic SQL.
• Experience with at least one cloud platform: Microsoft Azure, AWS, or Google Cloud.
• Hands-on experience with an LLM API, such as OpenAI, Anthropic, Gemini, or Azure OpenAI.
• Experience building an AI agent that calls tools or APIs, using a framework such as LangChain, LangGraph, or Semantic Kernel.
• Experience building a RAG pipeline, including document chunking, embeddings, vector search, and retrieval tuning.
• Experience building and consuming REST APIs, including authentication, rate limits, and versioning, with some exposure to API gateways.
• Experience connecting systems through webhooks, SDKs, or message queues, such as integrating an application with a CRM or database.
• Understanding of ML fundamentals, including embeddings, train/test splits, and evaluation metrics such as precision and recall.
• Professional written and spoken English and Spanish.
• Based in Colombia or Mexico.

Candidates with strong foundational knowledge and relevant academic, internship, research, or personal project experience are encouraged to apply.

Nice to Have

• Experience with speech AI or voice agent technologies, such as Azure AI Speech, Whisper, LiveKit, or Pipecat.
• Familiarity with the Model Context Protocol (MCP) or integration platforms such as Azure Logic Apps or n8n.
• Experience with CRM and contact center APIs, including Dynamics 365, Salesforce, or Zendesk.
• Familiarity with LLM evaluation tools such as Langfuse or Ragas.
• Cloud AI certifications or other relevant technical certifications.