F

Factored

End-to-end AI talent augmentation services

Senior Machine Learning Engineer - LLMs, Agentic Workflows

AI Application EngineeringConfirmed live in the last 24 hours
Full-time

About the Job

Requirements

  • At least 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, object-oriented programming, and application programming interface design and integration.
  • Proven experience designing and implementing agentic architectures, including multi-agent workflows, tool-calling, state management, and human-in-the-loop patterns.
  • Expertise integrating generative artificial intelligence frameworks and application programming interfaces, such as LangChain, LangGraph, OpenAI, and Claude, into production-grade applications.
  • Strong understanding of large language model fundamentals, systematic prompt engineering (chain-of-thought and few-shot), and debugging tools such as LangSmith or Arize Phoenix.
  • Experience with vector databases, such as Pinecone, Milvus, and Qdrant, for retrieval-augmented generation and long-term agent memory.
  • Experience with cloud platforms such as Amazon Web Services, Google Cloud Platform, or Microsoft Azure for deploying artificial intelligence workloads.

Responsibilities

  • Architect how an agent decomposes a complex user request into actionable subtasks.
  • Develop Plan-and-Execute or ReAct (Reason + Act) patterns in which the model reasons before acting.
  • Design systems to maintain short-term memory across long-running tasks and prevent agents from losing track of goals or entering infinite loops.
  • Create interfaces between large language models and external software, databases, or application programming interfaces.
  • Standardize how agents call functions, interact with legacy systems, or execute Python code in sandboxed environments.
  • Implement error handling and self-correction.
  • Build custom evaluation frameworks to measure trajectory success, including whether steps are efficient and safe as well as whether the final answer is correct.
  • Set up monitoring to visualize agent reasoning processes and identify where multi-step workflows fail.
  • Implement strict guardrails and human-in-the-loop checkpoints for high-stakes decisions to prevent hallucinated tool usage or unintended actions.

About the Company

Factored

End-to-end AI talent augmentation services

Factored provides end-to-end talent augmentation for AI, ML, and data science by sourcing, vetting, training, and managing remote engineering teams that integrate as extensions of a client's team. Their engineers, mainly from Latin America, work across all US time zones and can provide technical leadership, hands-on execution, or advisory support to accelerate AI roadmaps for US-based companies. They organize experts into Centers of Excellence (AI/ML, Data Science, Data Analytics, Data Engineering, Software Engineering) and apply projects like personalized recommendations, fraud detection, credit risk models, and automated data pipelines. Their differentiation comes from focusing exclusively on AI/data, using a vetted upskilling program developed with Stanford and deeplearning.ai, and offering nearshore talent with seamless integration to clients, with a goal to help organizations scale AI/data capabilities quickly and cost-effectively.

Company size
201-500
Company stage
Seed
Total funding
$2.5M
Headquarters
Mountain View, CA
Founded
2019

Recently Posted Jobs

Explore more opportunities at Factored

See more jobs