AI Engineer, Intern

Postman•San Francisco, CA

9h•Onsite

About The Position

Postman is seeking an AI Engineer Intern for its Summer 2026 AI Internship. The intern will work with the AI team on large-scale AI and agentic systems, from data pipelines through production deployment. The role involves owning scoped components of real systems with mentorship from senior engineers. Work spans benchmarks and evaluation, model training and efficiency, and agent-system engineering. The intern may contribute to APIFlow-Bench and an action-level AI safety benchmark; fine-tune open-weight models and evaluate training runs; assess low-bit quantized models; and help build Postman’s in-product Agent Mode, primarily in TypeScript. The intern will also document experiments, design decisions, and runbooks, and raise safety, fairness, or privacy concerns observed in model or agent behavior.

Requirements

Currently pursuing a BS, MS, or PhD in Computer Science, Data Science, or a related quantitative field.
Hands-on experience training or evaluating machine-learning models; coursework, research, hackathons, or a prior internship count.
Solid Python fundamentals, including data structures, functions, and basic testing, and comfort writing and reviewing code outside notebooks.
Working knowledge of at least one deep-learning framework; PyTorch is preferred.
Clear written and verbal communication, with a habit of documenting work.

Nice To Haves

Experience fine-tuning open-weight LLMs using SFT, LoRA, RL, or distillation, with improvements measured on a benchmark.
Experience building LLM agents or evaluation harnesses and benchmarks, and reporting results with statistical rigor.
A track record of shipping software end-to-end, such as APIs, services, CLIs, Docker, CI/CD, or cloud projects; public GitHub code is a plus.
Interest or experience in AI safety and robustness, including red-teaming, prompt injection, agent security, fairness, or interpretability.
Exposure to model-efficiency work such as quantization, low-bit inference, or serving optimization.
Evidence of rigor and initiative, such as publications, technical blog posts, ablation studies, or self-driven projects with quantified results.
Fluency with AI coding tools such as Claude Code, Cursor, or Codex, while maintaining a deep understanding of the systems built.

Responsibilities

Design and review benchmark tasks and mock API environments for APIFlow-Bench.
Extend the evaluation harness and task-generation pipeline in Python.
Help maintain the public multi-model leaderboard, including statistical confidence intervals.
Contribute to an action-level AI safety benchmark through scenario design, threat modeling, and auditable evaluation design.
Fine-tune open-weight models for tool calling and agentic tasks using SFT, distillation, and RL.
Design and run model-training experiments; evaluate runs on benchmarks, support ablation studies and error analysis, track experiments, and report results including costs.
Evaluate ultra-low-bit quantized models for on-device use and analyze differences from full-precision models.
Help build Postman’s in-product AI agent, Agent Mode, using a minimal architecture with LLM API calls, tool loops, multi-step execution, and checkpointing.
Review open-source agent harnesses and translate findings into design specifications and prototypes.
Document experiments, design decisions, and runbooks, and flag safety, fairness, or privacy concerns.