Design agent planning patterns that break complex requests into sub-tasks
Build the interface between LLMs and external software, databases, or APIs
Design short-term memory so long-running agents keep their goal and avoid loops
Build custom evaluation frameworks that measure trajectory success and safety
Add guardrails and human-in-the-loop checkpoints for high-stakes decisions
From the employer’s posting
Architect how the agent breaks down a complex user request into a series of actionable sub-tasks.
Create the interface between the LLM and external software, databases, or APIs.
Design robust systems to maintain "short-term memory" across long-running tasks, ensuring the agent doesn't lose track of its goal or get stuck in infinite loops.
Build custom evaluation frameworks to measure trajectory success—not just whether the final answer was right, but if the steps taken to get there were efficient and safe.
Ensure the agent doesn't "hallucinate" tool usage or take unintended actions through strict guardrails and Human-in-the-Loop (HITL) checkpoints for high-stakes decisions.
5+ years of hands-on experience developing and deploying machine learning models in production environments.
Proven experience designing and implementing agentic architectures, including multi-agent workflows, tool-calling, state management, and human-in-the-loop patterns.
Expertise in integrating Generative AI frameworks and APIs (such as LangChain, LangGraph, OpenAI, and Claude) into production-grade applications.
Strong understanding of LLM fundamentals, systematic prompt engineering (chain-of-thought, few-shot), and debugging tools like LangSmith or Arize Phoenix.
Experience with vector databases (Pinecone, Milvus, Qdrant) for retrieval-augmented generation (RAG) and long-term agent memory.
Experience with cloud platforms such as AWS, GCP, or Azure for deploying AI workloads.
Qualification wording
5+ years of hands-on experience developing and deploying machine learning models in production environments.
Proven experience designing and implementing agentic architectures, including multi-agent workflows, tool-calling, state management, and human-in-the-loop patterns.
Expertise in integrating Generative AI frameworks and APIs (such as LangChain, LangGraph, OpenAI, and Claude) into production-grade applications.
Strong understanding of LLM fundamentals, systematic prompt engineering (chain-of-thought, few-shot), and debugging tools like LangSmith or Arize Phoenix.
Experience with vector databases (Pinecone, Milvus, Qdrant) for retrieval-augmented generation (RAG) and long-term agent memory.
Experience with cloud platforms such as AWS, GCP, or Azure for deploying AI workloads.
We are a transparent workplace, where EVERYBODY has a voice in building OUR company, and where learning and growth are available to everyone based on their merits, not just on stamps on their resume. As impressive as some of the stamps on our resumes are, we recognize that human talent and passion exist everywhere, and come from many backgrounds, so stamps matter much less than results. All of us are dedicated doers and are highly energetic, focusing vehemently on execution because we know that the best learning happens by doing. We recognize that we are creating OUR COMPANY TOGETHER, which is not only a high-performing fast-growing business but is changing the way the world perceives the quality of technical talent in Latin America. We are fueled by the great positive impact we are making in the places where we do business and are committed to accelerating careers and investing in hundreds (and hopefully thousands) of highly talented data science engineers and data analysts.
Open 4 monthsWe first saw this posting 130 days ago and it is still up. Roles open this long are often slow to fill or kept open to collect applications.
Status in our records
Live
First seen by us
Jul 15, 2026130 days ago
Recorded sightings
69
Last seen by us
Nov 22, 2026
Jul 15, 2026today
These dates show when we found the posting. Check the employer’s website to confirm it is still accepting applications.
How this job compares
Time since we first saw it
Day 130
776
Up longer than most. Similar jobs usually come down between day 7 and day 76.
From 6,389 similar postings that came down. Coming down is not always a hire.
Add your resume and we’ll mark which of these tools you already use, and point out anything in the posting that could rule you out.
Python
AWS
Azure
GCP
Where the posting names them
- Create the interface between the LLM and external software, databases, or APIs.
- Standardize how the agent calls functions, interacts with legacy systems, or executes Python code in a sandboxed environment.
- Implement error-handling and self-correction.
- Experience with vector databases (Pinecone, Milvus, Qdrant) for retrieval-augmented generation (RAG) and long-term agent memory.
- Experience with cloud platforms such as AWS, GCP, or Azure for deploying AI workloads.
Our Benefits:
Complete your application on job-boards.greenhouse.io. The employer’s form will show what is required.
Applying through Greenhouse
No account needed: the form is one page, with an “Autofill my application” option that reads your resume.
Greenhouse doesn’t read resumes over 2.5 MB, or details placed in a header, footer, text box, table or second column. The file still attaches, but a recruiter has to type you in by hand.
Founded in Palo Alto by Dr. Andrew Ng and Israel Niezen, Factored helps U.S. companies build and scale world-class AI, ML, and Data teams, powered by the top 1% of LATAM talent, with a defining purpose: To empower brilliant humans, unleash their potential, and amplify their impact in the world.
At Factored, you’ll be part of a community that values learning, ownership, and authenticity, where your growth is personal and your ideas matter. We’re transparent, curious, and collaborative. We strive for excellence, celebrate diversity, encourage curiosity, and build an environment where you can truly thrive.
As a Machine Learning Engineer specializing in Agentic Workflows, you will design and deliver advanced autonomous AI agents and multi-agent systems that power complex, mission-critical applications for enterprise environments. You’ll work across LLM orchestration frameworks, state management, tool execution, and fine-tuning techniques, owning intelligent automation systems end-to-end from prototyping to production deployment.
Functional Responsibilities:
Architect how the agent breaks down a complex user request into a series of actionable sub-tasks.
Develop "Plan-and-Execute" or "ReAct" (Reason + Act) patterns where the model thinks before it acts.
Design robust systems to maintain "short-term memory" across long-running tasks, ensuring the agent doesn't lose track of its goal or get stuck in infinite loops.
Create the interface between the LLM and external software, databases, or APIs.
Standardize how the agent calls functions, interacts with legacy systems, or executes Python code in a sandboxed environment.
Implement error-handling and self-correction.
Build custom evaluation frameworks to measure trajectory success—not just whether the final answer was right, but if the steps taken to get there were efficient and safe.
Set up monitoring to visualize the agent's "thought process" and identify exactly where a multi-step workflow broke down.
Ensure the agent doesn't "hallucinate" tool usage or take unintended actions through strict guardrails and Human-in-the-Loop (HITL) checkpoints for high-stakes decisions.
Qualifications:
5+ years of hands-on experience developing and deploying machine learning models in production environments.
Strong software engineering fundamentals, including data structures, algorithms, system design, OOP, and API design & integration.
Proven experience designing and implementing agentic architectures, including multi-agent workflows, tool-calling, state management, and human-in-the-loop patterns.
Expertise in integrating Generative AI frameworks and APIs (such as LangChain, LangGraph, OpenAI, and Claude) into production-grade applications.
Strong understanding of LLM fundamentals, systematic prompt engineering (chain-of-thought, few-shot), and debugging tools like LangSmith or Arize Phoenix.
Experience with vector databases (Pinecone, Milvus, Qdrant) for retrieval-augmented generation (RAG) and long-term agent memory.
Experience with cloud platforms such as AWS, GCP, or Azure for deploying AI workloads.
Our Benefits:
Ownership through equity participation.
Annual company retreat.
Education bonus for continuous learning.
Company-wide winter break.
Paid time off.
Optional in-person events and meetups.
Tailored career roadmaps.
High-performance culture.
At Factored, we believe that passionate, smart people expect honesty and transparency, as well as the freedom to do the best work of their lives while learning and growing as much as possible. Great people enjoy working with other passionate, smart people, so we believe in hiring right, and are very selective about who joins our team. Once we hire you, we will invest in you and support your career and professional growth in many meaningful ways. We hire people who are supremely intelligent and talented, but we recognize that intelligence is not enough. Perhaps more importantly, we look for those who are also passionate about our mission and are honest, diligent, collaborative, kind to others, and fun to be around. Life is too short to work with people who don’t inspire you.
We are a transparent workplace, where EVERYBODY has a voice in building OUR company, and where learning and growth are available to everyone based on their merits, not just on stamps on their resume. As impressive as some of the stamps on our resumes are, we recognize that human talent and passion exist everywhere, and come from many backgrounds, so stamps matter much less than results. All of us are dedicated doers and are highly energetic, focusing vehemently on execution because we know that the best learning happens by doing. We recognize that we are creating OUR COMPANY TOGETHER, which is not only a high-performing fast-growing business but is changing the way the world perceives the quality of technical talent in Latin America. We are fueled by the great positive impact we are making in the places where we do business and are committed to accelerating careers and investing in hundreds (and hopefully thousands) of highly talented data science engineers and data analysts.
In short, our business is about people, so we hire the best people and invest as much as possible in making them fall in love with their work, their learning, and their mission. When not nerding out on data science, we love to make music together, play sports, play games, dance salsa, cook delicious food, brew the best coffee, throw the best parties, and generally have a great time with each other.
Demand for ML Engineer roles
New ML Engineer postings at the employers we follow are down 4% over the last 6 weeks compared with the 6 before.
August 17Last week
Each bar is one week of new postings. The darkest bars are the last 6 weeks.
Counted from the hiring pages we’ve followed for at least five weeks, so employers we add don’t look like growth. Updated weekly.
About the role
We file this job under ML Engineer, by the work the posting describes.
ML engineers put machine learning models into products. They write the code that trains, ships, serves and monitors models so a recommendation or prediction works for real users.
Postings ask for strong Python and software engineering, a framework such as PyTorch, cloud services, and more and more often experience with large language models.
A data scientist often works out which model to build; an ML engineer makes it run reliably in production.
US government figures for computer and information research scientists
Median yearly pay, May 2025
$140,300
Expected change, 2025 to 2035
21.8% more jobsagainst 3.5% for all jobs
The government has no code for ML engineers, so these figures are for the closest group, computer and information research scientists.
Selected passages from the saved posting. Check the full description for conditions and exceptions.
Pay
No pay amount identified in the saved description.
Location & working pattern
Latin America
Fully remote | Complete engagement job
Founded in Palo Alto by Dr. Andrew Ng and Israel Niezen, Factored helps U.S. companies build and scale world-class AI, ML, and Data teams, powered by the top 1% of LATAM talent, with a defining purpose: To empower brilliant humans, unleash their potential, and amplify their impact in the world.
Work authorization
No clear work-authorization passage found. Eligibility is unconfirmed.