Back to jobs

Tech Lead

Latin America - Remote

Enumerate is hiring a Lead Full Stack AI Engineer (Tech Lead) to lead the technical development of AI-powered product capabilities. This is a deeply hands-on engineering role for an experienced full-stack developer who has built production applications using Large Language Models (LLMs), understands modern AI application architectures, and brings strong data engineering instincts. The Tech Lead will be responsible for both defining the technical approach and personally implementing critical parts of the solution. This is not a management-only or architecture-only position. The successful candidate will write production code daily while providing technical direction, mentoring developers, and ensuring high-quality execution across a small, fast-moving AI Pod. The role works closely with Product Management and Platform leadership to translate product opportunities into reliable, scalable AI-powered features. 

This is a remote contractor opportunity for candidates located in LATAM who are comfortable working in an English-speaking professional environment. 

Key Responsibilities  

AI Solution Delivery & Architecture  

  • Lead the design, implementation, and production deployment of AI-powered product features using LLMs and modern AI application architectures. 
  • Architect and personally develop LLM integrations, retrieval-augmented generation (RAG) pipelines, embeddings, vector search, and tool/function calling capabilities. 
  • Design and implement agentic workflows that combine LLM reasoning, enterprise data retrieval, business logic, and application actions. 
  • Make informed architectural decisions regarding model selection, orchestration frameworks, context management, and retrieval strategies. 
  • Build reusable AI services and components that can support multiple product features. 
  • Implement robust error handling, fallbacks, human-in-the-loop controls, and safeguards for AI-driven workflows. 
  • Optimize AI systems for accuracy, reliability, latency, scalability, and cost. 
  • Evaluate emerging AI frameworks and capabilities, selecting technologies based on practical product and engineering needs. 

Data Architecture & AI integration 

  • Design data access and retrieval architectures that enable AI applications to operate reliably on enterprise data. 
  • Work across relational databases, data lakes, APIs, and structured/unstructured data sources. 
  • Understand data lake and lakehouse architectures, ingestion patterns, transformation pipelines, and analytical data models. 
  • Apply strong judgment around data quality, lineage, freshness, consistency, and authoritative sources. 
  • Design retrieval strategies that combine structured queries, semantic search, and application-specific business logic. 
  • Collaborate with Data Engineering to establish reliable, governed data access patterns for AI applications. 
  • Ensure appropriate data security, access controls, and privacy safeguards when integrating enterprise data with LLMs. 
  • Identify and address data quality or architectural limitations that could affect AI accuracy and reliability. 

AI Quality, Evaluation and Operational Excellence 

  • Establish practical evaluation and testing approaches for LLM-powered features, including response quality, grounding, correctness, and regression testing. 
  • Implement observability for AI workflows, including model usage, latency, token consumption, cost, failures, and application-level outcomes. 
  • Design mechanisms to detect and mitigate hallucinations, unreliable outputs, and inappropriate AI actions. 
  • Implement appropriate human approval, auditability, and explainability mechanisms for AI-assisted decisions. 
  • Ensure AI functionality operates securely and reliably within existing application and cloud infrastructure. 
  • Drive continuous improvement through production telemetry, user feedback, and experimentation. 
  • Establish reusable engineering patterns for testing, deploying, and operating AI-enabled features. 

 Pod Leadership & Execution  

  • Act as the technical lead for a cross-functional AI Pod.  
  • Break down product requirements into executable technical workstreams and prototypes.  
  • Guide rapid iteration cycles, proofs-of-concept, and MVPs, balancing experimentation with production readiness.  
  • Review code, architecture, and technical decisions to maintain quality and velocity.  

Product & Data Collaboration  

  • Partner closely with Product Management to shape problem definitions, success metrics, and delivery plans.  
  • Collaborate with the Product Leader to integrate models, analytics, and data assets into product workflows.  
  • Translate Data outputs into consumable APIs, services, and product features.  
  • Provide technical feedback on feasibility, scope, and tradeoffs during product discovery.  

Operationalization & Quality  

  • Ensure features are production-grade, including monitoring, logging, and performance tracking.  
  • Implement guardrails around AI usage, including reliability, latency, cost controls, and failure modes.  
  • Support experimentation frameworks, A/B testing, and post-launch learning loops.  
  • Drive responsible AI practices, including explainability, bias awareness, and data privacy considerations.  

Technical Standards & Enablement  

  • Define and enforce lightweight engineering standards for AI-enabled systems.  
  • Promote reuse of components, prompts, pipelines, and services across AI initiatives.  
  • Mentor pod engineers on AI-adjacent system design and best practices.  
  • Contribute to internal documentation and shared AI patterns/playbooks.  

  Required Qualifications  

  • 7+ years of professional software engineering experience, including significant hands-on development of production applications. 
  • Strong full-stack engineering capabilities, including modern frontend frameworks such as React or Vue and backend development using Python, Node.js, Java, or similar technologies. 
  • Demonstrated experience designing, building, and shipping production LLM-powered applications or AI-enabled product features. 
  • Strong practical knowledge of the modern LLM application stack, including prompting, RAG, embeddings, vector search, model APIs, and tool/function calling. 
  • Experience designing AI application architectures that integrate LLMs, backend services, enterprise data, and business workflows. 
  • Strong understanding of databases, data modeling, data pipelines, and data lake concepts. 
  • Ability to design reliable data retrieval and integration patterns for AI applications. 
  • Experience designing and building scalable APIs, backend services, and cloud-native applications. 
  • Strong software engineering fundamentals, including automated testing, observability, debugging, and production operations. 
  • Experience providing technical leadership through architecture decisions, code reviews, mentoring, and hands-on collaboration. 
  • Demonstrated ability to independently solve complex technical problems while remaining an active individual contributor. 
  • Experience working closely with Product teams in fast-moving, iterative environments. 
  • BS/MS in Computer Science, Engineering, or related discipline, or equivalent practical experience. 

  

Preferred Qualifications  

  • Experience designing and implementing agentic AI systems, including multi-step workflows, tool orchestration, and human-in-the-loop patterns. 
  • Familiarity with LLM frameworks such as LangChain, LlamaIndex, LangGraph, or similar technologies. 
  • Experience with AI evaluation frameworks, model observability, prompt/version management, and production AI monitoring. 
  • Experience with AWS data and AI services, including S3, Athena, Glue, Bedrock, or comparable technologies. 
  • Familiarity with data lakehouse architectures and medallion data patterns. 
  • Experience combining structured data retrieval, SQL, and semantic search in AI applications. 
  • Experience building AI capabilities within enterprise SaaS applications. 
  • Experience with workflow orchestration frameworks such as Temporal or similar technologies. 
  • Familiarity with AI security considerations, including prompt injection, data leakage, and permission-aware retrieval. 
  • Experience leading small engineering teams while remaining a substantial individual contributor. 

What Success Looks Like 

  • Personally deliver complex AI-powered product features while guiding a small team of developers. 
  • Establish a pragmatic, reusable technical foundation for LLM-powered and agentic product capabilities. 
  • Build reliable integrations between AI models, enterprise data, and existing application workflows. 
  • Make sound architectural decisions that balance delivery speed, AI quality, scalability, and operational cost. 
  • Raise the technical capabilities and productivity of pod developers through hands-on mentoring and collaboration. 
  • Deliver production AI features that are secure, observable, maintainable, and demonstrably valuable to customers. 

Total monthly compensation:

$3,500 - $4,500 USD

Create a Job Alert

Interested in building your career at Enumerate? Get future opportunities sent straight to your email.

Apply for this job

*

indicates a required field

Phone
Resume/CV*

Accepted file types: pdf, doc, docx, txt, rtf


Education

Select...
Select...

Select...

By submitting this application, you acknowledge that Enumerate (“we,” “us,” or “our”) will collect, use, and process the personal information you provide to evaluate your application, communicate with you, and manage our recruitment process. Enumerate is the data controller for purposes of candidate information where applicable.

Information We Collect:  We may collect the following types of personal information during the recruitment process:

  • Identification and contact details (e.g., name, phone number, email, address)
  • Employment, education, qualifications, and professional history
  • Application materials such as resumes, cover letters, portfolios, assessments, or interview notes
  • Information required to verify eligibility to work or comply with legal requirements
  • Any additional information you voluntarily provide during the recruitment process

Your information will be accessed only by authorized Enumerate personnel and trusted third-party service providers who support our hiring and applicant tracking activities. These service providers are subject to confidentiality and data protection obligations.

International Transfers: If you are located outside the United States, your information may be transferred and processed in the United States or other jurisdictions. Where required, we implement appropriate safeguards such as Standard Contractual Clauses to protect your data when transferred internationally.

Legal Basis for Processing (EU/EEA & UK):  If you are located in the EU/EEA or the UK, we process your personal data on the following legal bases:

  • Legitimate Interest: Evaluating and managing candidates and taking steps at your request prior to entering into an employment contract.
  • Legal Obligation: Complying with applicable employment, reporting, or regulatory requirements.
  • Consent: If you choose to join our talent pool or receive future job opportunities or communications.

You may withdraw consent at any time without affecting prior processing. You also have the right to file a complaint with your local supervisory authority if you believe your rights have been violated.

California Residents (CCPA/CPRA):  If you are a California resident, you have rights under the California Consumer Privacy Act (CCPA), as amended by the CPRA, including:

  • Right to Know the categories of personal information we collect and the purposes for which we use it.
  • Right to Request Access, Correction, or Deletion of your personal information.
  • Right to Limit the Use of Sensitive Personal Information, if applicable.
  • Right to Non-Discrimination for exercising your privacy rights.

Enumerate does not sell or share candidate personal information as defined under the CCPA/CPRA.

Data Retention:  We retain personal information of applicants for up to 12 months, unless a longer period is required by law.
If you consent to join our talent pool, we may retain your information for up to 24 months to consider you for future opportunities.

Your Rights: You may request:

  • Access to your data
  • Correction of inaccurate information
  • Deletion of your data
  • Withdrawal of consent (if applicable)

To exercise your rights, contact: PeopleOps@goenumerate.com

Select...
Select...