As an Agentic AI/ML Engineer Intern, you will build agentic solutions that turn FieldAI’s data and tooling into actionable support and insights. Your work has a dual focus: creating internal agents that accelerate our engineering and operations workflows, and building external agentic experiences to help customers gain insights from their deployments. The critical foundation for both is the AI Ops platform you will help build—developing the core infrastructure for orchestration, tool integration, memory, and observability. This is a hands-on role where you will prototype, evaluate, and ship agent-native solutions that directly multiply the impact of our teams and technology.
This role is crucial to how we scale. As our fleet, customer base, and team grow quickly, the agentic solutions and AI Ops infrastructure you build are what let us support more customers, surface more insights, and run our own operations without scaling headcount linearly. Your work directly multiplies what every engineer, field team, and customer can do — making it a high-leverage part of the company’s next phase of growth. This is a paid internship with a strong opportunity to convert to a full-time role based on performance and business needs.
What You'll Do
Design and implement agentic workflows with tool use, memory, and orchestration to automate repetitive tasks and answer questions over internal and customer-facing data.
Contribute to AI Ops (agent infrastructure) — orchestration, evals, and observability — and apply it to enable agent-native DevOps that automates our engineering and internal operations workflows.
Build and optimize RAG pipelines with vector DBs and knowledge graphs to ground agents in the right context.
Set up evaluation pipelines to measure agent quality, reliability, and performance.
What You Bring
Educational Track: Currently pursuing a BS, MS, or Ph.D. in Computer Science, AI/ML, Robotics, or a related technical field, with deep project-based experience.
Strong evidence of building agentic projects (hackathons, research, internships, or personal projects).
Agentic & ML Foundation: Solid theoretical understanding and practical application of Agentic Engineering principles (Tool Use, Memory, RAG, Planning).
Production-Grade Python: Proven ability to write reliable, testable, clean, and performant Python code, with familiarity with software engineering best practices, including version control, containerization (Docker), and test-driven development (pytest).
Advanced Agent Orchestration: Hands-on engineering experience with modern, open-source agentic frameworks (e.g., LangChain, LangGraph, LlamaIndex) rather than relying strictly on service-managed agent APIs.
AI Ops & Observability: Experience implementing evaluation, tracing, and monitoring pipelines (e.g., MLflow, Langfuse, TruLens) to quantitatively measure agent quality, factual accuracy, latency, and reliability.
Information Retrieval & Grounding: Practical expertise building and optimizing context-aware systems, with hands-on experience using Vector Databases (e.g., Pinecone, FAISS, OpenSearch) and designing Knowledge Graphs to reliably ground agents and mitigate hallucinations.
Cloud / Robot Compute: Familiarity with Cloud Platforms (e.g., AWS, GCP) for ML/AI deployment, and/or experience with on-robot compute environments.
Bias for action and ownership: Ability to take a loosely defined, complex problem and define and drive a working solution end-to-end.
Strong ability to drive solutions end-to-end, including cross-team coordination and seeking out customer input to shape what gets built.
Strong communication, initiative, and ability to learn quickly in a fast-moving team.
What Sets You Apart
Deep experience designing and operating AI Ops infrastructure at production scale, including robotics-grade data logging and observability (e.g., Foxglove).
Experience with advanced agent patterns: Multi-Agent Systems, Human-in-the-Loop workflows, or Long-Horizon Planning.
Prior experience shipping internal tools or customer-facing assistants used by real users.
Personal projects and a portfolio of agentic builds are a big bonus — we love seeing what you’ve shipped on your own.
Skills Required
- Currently pursuing BS, MS, or PhD in Computer Science, AI/ML, Robotics, or related technical field
- Strong evidence of building agentic projects (hackathons, research, internships, personal projects)
- Solid understanding and practical application of Agentic Engineering principles (Tool Use, Memory, RAG, Planning)
- Production-grade Python development: reliable, testable, clean, performant code
- Familiarity with software engineering best practices including version control, containerization (Docker), and test-driven development (pytest)
- Hands-on engineering experience with open-source agentic frameworks (e.g., LangChain, LangGraph, LlamaIndex)
- Experience implementing evaluation, tracing, and monitoring pipelines (e.g., MLflow, Langfuse, TruLens)
- Practical experience with Vector Databases (e.g., Pinecone, FAISS, OpenSearch) and designing Knowledge Graphs for grounding agents
- Familiarity with cloud platforms for ML/AI deployment (AWS, GCP) and/or on-robot compute environments
- Bias for action, ownership, and ability to drive loosely defined problems end-to-end including cross-team coordination
- Strong communication, initiative, and ability to learn quickly in fast-moving teams
- Experience designing and operating AI Ops infrastructure at production scale (robotics-grade logging/observability, e.g., Foxglove)
- Experience with multi-agent systems, human-in-the-loop workflows, or long-horizon planning
- Prior experience shipping internal tools or customer-facing assistants used by real users
- Personal projects and portfolio of agentic builds
What We Do
FieldAI is pioneering the development of a field-proven, hardware agnostic brain technology that enables many different types of robots to operate autonomously in hazardous, offroad, and potentially harsh industrial settings – all without GPS, maps, or any pre-programmed routes.
