Agentic AI/ML Engineer

Design and build agentic workflows that leverage tool use, memory, planning, and orchestration to automate repetitive tasks and enable natural-language access to internal and customer-facing data.

Contribute to FieldAI's AI Ops platform by developing agent infrastructure for orchestration, evaluation, observability, and reliability. Apply these capabilities to create agent-native DevOps workflows that automate engineering, support, and operational processes.

Develop and optimize retrieval systems, including RAG pipelines, vector databases, and knowledge graph integrations, to provide agents with accurate, relevant, and scalable context.

Build evaluation frameworks and automated testing pipelines to measure agent quality, reliability, safety, latency, and business impact, and use those insights to continuously improve system performance.

Prototype, iterate, and deploy AI-powered tools that improve internal productivity and deliver actionable insights to customers.

Partner closely with engineering, product, field operations, and customer-facing teams to identify high-leverage opportunities for automation and agent-driven workflows.

BS, MS, or Ph.D. in Computer Science, Artificial Intelligence, Machine Learning, Robotics, or a related technical field, or equivalent hands-on experience. Recent graduates and candidates with up to approximately one year of professional experience are encouraged to apply.

Strong evidence of building and shipping AI or agentic systems through academic research, internships, hackathons, open-source contributions, or personal projects.

Solid understanding of modern agentic AI concepts, including tool use, memory, retrieval-augmented generation (RAG), planning, and multi-step reasoning, with experience applying these concepts in real-world projects.

Strong Python engineering skills, including writing clean, maintainable, testable, and performant code. Familiarity with software engineering best practices such as version control, containerization (Docker), CI/CD, and automated testing.

Hands-on experience with modern agent frameworks and orchestration systems such as LangGraph, LangChain, LlamaIndex, CrewAI, or similar technologies.

Experience building, evaluating, and improving AI systems through structured testing, benchmarking, observability, tracing, and monitoring frameworks.

Familiarity with retrieval and grounding techniques, including vector databases, semantic search, knowledge graphs, and other approaches used to improve agent accuracy and reliability.

Experience working with cloud platforms such as AWS, GCP, or Azure for deploying and operating AI/ML systems. Experience with robotics, edge computing, or on-device AI systems is a plus.

Demonstrated ownership and bias for action, with the ability to take an ambiguous problem, break it down into actionable steps, and deliver working solutions.

Strong collaboration and communication skills, including the ability to work across engineering, product, operations, and customer-facing teams to understand requirements and drive outcomes.

Curiosity, initiative, and a desire to learn quickly while contributing in a fast-paced, high-growth environment.

Experience building, operating, or contributing to AI infrastructure, evaluation systems, observability platforms, or data pipelines that support production AI applications.

Familiarity with advanced agentic patterns such as multi-agent systems, human-in-the-loop workflows, long-horizon planning, tool orchestration, or autonomous task execution.

Experience building AI-powered products, internal developer tools, copilots, assistants, or workflow automation systems used by real users.

Exposure to robotics, autonomy, edge computing, or large-scale operational systems.

Familiarity with observability and debugging tools for AI and robotic systems, such as Langfuse, MLflow, Weights & Biases, Foxglove, or similar platforms.

Contributions to open-source projects, research publications, technical blogs, competition results, or other publicly available work that demonstrates technical depth and initiative.

A portfolio of personal projects, hackathon submissions, or agentic applications you've designed and shipped independently. We love seeing what you've built.