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.
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 Senior AI Engineer at Factored, you will engage full-time in designing and building production-grade GenAI systems that transform enterprise AI strategies into secure, scalable applications. You are a hands-on engineer working directly with client teams, shipping production code while contributing to technical strategy and learning from experienced leaders. You own complex, high-impact projects from architecture through optimization and deployment. This role exists for engineers who want to build at the frontier of AI while growing their technical expertise.
Functional Responsibilities:
- Architect, design, and implement backend Python systems that integrate with LLMs via the Model Context Protocol (MCP), ensuring services are scalable, secure, and production-ready.
- Implement complex, stateful agentic architectures and reasoning loops for multi-step AI workflows using frameworks like LangGraph.
- Build, deploy, and manage cloud-native AI applications on AWS (Bedrock, Lambda, ECS) and other modern infrastructure.
- Champion Spec-Driven Development (SDD) and Context-Driven Development (CDD) to ensure models produce deterministic, highly structured outputs.
- Architect semantic memory layers and build advanced RAG pipelines utilizing vector databases to optimize performance.
- Implement AI security guardrails, strict boundary controls, and Human-in-the-Loop (HITL) approval flows to ensure compliance, privacy, and safety.
- Monitor application health with observability tools (APM, LangSmith, Phoenix) to track agent trajectories, LLM performance metrics, and proactively resolve performance issues.
- Act as an internal AI accelerator by onboarding teams, building reusable prompts, and automating repetitive workflows to drive the adoption of AI-native developer tools (Claude Code, Cursor) org-wide.
- Collaborate with ML Engineers, product managers, and cross-functional teams to understand requirements and deliver AI features that drive measurable value.
- Communicate technical architecture and trade-offs clearly to stakeholders at all levels.
- Contribute to raising engineering standards through code review and knowledge sharing, treating prompts and context strictly as code.
Qualifications:
- 5+ years of professional experience as a Software Engineer or in a related role, with a strong foundation in Python.
- Hands-on experience with modern Generative AI orchestration frameworks (LangGraph, LangChain, AutoGen) and agentic state management.
- Practical experience with the Model Context Protocol (MCP), function calling, tool-use APIs, and enforcing structured outputs across major foundation models.
- Experience with cloud platforms like AWS (including Bedrock), building, deploying, and managing cloud-native applications; exposure to Azure or GCP is also valuable.
- Experience designing and developing APIs using frameworks like FastAPI or Django to wrap agentic workflows into consumable backend services.
- Strong system design and problem-solving skills, capable of visualizing and debugging complex, non-linear agent trajectories and AI workflows.
- Practical experience with databases (PostgreSQL or NoSQL) and vector databases (Pinecone, Qdrant, Milvus) for semantic memory and RAG workflows.
- Proficiency with DevOps and CI/CD tools such as Docker, Kubernetes, Terraform, and Git-based workflows.
- Excellent English communication skills, both written and spoken, with the ability to collaborate effectively with global teams and explain complex AI concepts clearly.
- Comfortable translating between technical and business perspectives and managing ambiguous requirements.
- A growth mindset and genuine interest in learning and applying new AI methodologies (like SDD and CDD) to real-world challenges
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.
Skills Required
- 5+ years of software development experience with a focus on AI/ML
- Proficiency in Python and server-side frameworks such as FastAPI
- Understanding of cloud platforms (AWS, GCP, Azure) and experience deploying applications
- Familiarity with containerization and orchestration technologies such as Docker and Kubernetes
- Exposure to Generative AI technologies and frameworks like LangChain or LangGraph
- Experience with deep learning frameworks (HuggingFace, PyTorch, TensorFlow)
- Understanding of modern development practices, including version control and CI/CD
- Strong problem-solving skills and attention to detail
- Effective communicator with the ability to collaborate across teams
- Passion for learning and staying current with AI/ML advancements
What We Do
Factored (backed by Andrew Ng's AI Fund and deeplearning.ai) helps leading tech companies select, upskill, and build world-class data science, machine learning and AI engineering teams much faster and more cost effectively. Our engineers have been personally vetted, educated, and mentored by some of the most talented and recognized AI educators and engineers from Silicon Valley, Stanford University and deeplearning.ai.
.png)
