# Senior AI Engineer (Internal Tools & Agents) at Jobgether

> Remote · Colombia · Senior · ML / AI · open. Source: https://alderhq.app/jobs/lever%3Ajobgether%3Ad6b2b4e8-e23a-40e4-8ae4-e4a8ff4c7e8c (read 2026-11-21).

## Facts (observed)

- Company: [Jobgether](https://alderhq.app/companies/jobgether)
- Location text: Colombia
- Where it can be done from (inferred): Remote · Colombia (evidence: "Location: Colombia")
- Posted: 2026-11-20 (1 days ago)
- First seen by alder: 2026-11-20 · last verified: 2026-11-21
- Reposted: 0 times · edited: 0 times
- Apply on the employer's site: https://jobs.lever.co/jobgether/d6b2b4e8-e23a-40e4-8ae4-e4a8ff4c7e8c
- Skills listed (inferred): Python, Go, LLMs

## Pay and sponsorship

- Posted pay: not posted

## Description (the employer's text)

### Accountabilities

Design, develop, maintain, and improve AI-powered internal tools that streamline workflows and support better business decisions.

Build sophisticated Agent workflows incorporating context management, tool calling, knowledge retrieval, structured outputs, state management, and human approval or escalation processes.

Integrate AI applications with internal data sources, APIs, business systems, and third-party services.

Develop reliable and scalable backend services and APIs that support production AI applications.

Work directly with internal stakeholders to understand operational processes, identify pain points, and define measurable success criteria.

Translate ambiguous business requirements into clear, testable, and deliverable technical solutions.

Measure the impact of deployed tools through adoption, task-completion quality, time savings, error reduction, and other relevant performance indicators.

Use production data, user feedback, and observed failures to prioritize improvements and continuously enhance solutions.

Create evaluation datasets and regression tests for prompts, models, retrieval pipelines, tools, and end-to-end workflows.

Establish release validation processes to detect quality regressions and unintended effects before deployment.

Compare models and technical approaches based on output quality, latency, reliability, security, and cost.

Implement robust handling of timeouts, retries, rate limits, asynchronous jobs, partial failures, and third-party dependency issues.

Build and maintain logging, tracing, monitoring, versioning, and recovery mechanisms for AI workflows.

Apply appropriate access controls, data-handling policies, human approval steps, and audit trails for sensitive internal processes.

Troubleshoot issues across model behavior, prompts, knowledge sources, retrieval quality, tool responses, business rules, and backend infrastructure.

Collaborate with AI engineers and stakeholders across Product, Engineering, Operations, and other functions to deliver effective solutions.

Communicate technical feasibility, risks, costs, trade-offs, and alternative approaches clearly, while breaking larger initiatives into manageable delivery stages.

Proactively communicate progress, blockers, timelines, and next steps, and document systems and technical decisions to support long-term maintainability.

### Requirements

At least 4 years of professional software engineering experience, with strong backend development fundamentals.

At least 1–2 years of hands-on experience building LLM-powered applications, Agent workflows, or AI automation systems.

Demonstrated experience launching AI applications for real users and improving them using production data and user feedback.

Practical experience with tool calling, retrieval-augmented generation (RAG), knowledge retrieval, workflow orchestration, structured outputs, and stateful Agent systems.

Experience developing production services, APIs, data pipelines, and integrations with internal or third-party systems.

Strong hands-on proficiency in Golang. Golang is used for production development, and candidates must be able to complete the technical coding assessment in this language.

Practical Python experience for LLM and AI application development.

Experience creating evaluation datasets, regression tests, monitoring systems, and release validation processes for LLM applications.

Strong debugging and problem-solving skills across models, prompts, retrieval systems, tools, application logic, and backend infrastructure.

Strong ownership and accountability, including the ability to identify risks early, follow through after launch, and verify that delivered solutions achieve their intended outcomes.

Fluent spoken and written English, as it is the working language for daily communication and collaboration.

Clear communication and collaboration skills, particularly in distributed and cross-functional teams.

Nice to have:

Experience developing internal productivity tools, enterprise AI applications, or workflow automation platforms.

### How Jobgether works

We use an AI-powered matching process to ensure your application is reviewed quickly, objectively, and fairly against the role's core requirements. Our system identifies the top-fitting candidates, and this shortlist is then shared directly with the hiring company. The final decision and next steps (interviews, assessments) are managed by their internal team.

We appreciate your interest and wish you the best!

Why Apply Through Jobgether?

Data Privacy Notice: By submitting your application, you acknowledge that Jobgether will process your personal data to evaluate your candidacy and share relevant information with the hiring employer. This processing is based on legitimate interest and pre-contractual measures under applicable data protection laws (including GDPR). You may exercise your rights (access, rectification, erasure, objection) at any time.

#LI-CL1

---
Data: alder (https://alderhq.app). Cite https://alderhq.app/jobs/lever%3Ajobgether%3Ad6b2b4e8-e23a-40e4-8ae4-e4a8ff4c7e8c and the date you read it. Observed facts come from the employer's own listing; location reach, level, family and skills are inferences.
