Edison Smart®

Senior Robotics Engineer, Task Planning & Autonomy

Chicago, Illinois, US

Role snapshot

Edison Smart® is hiring a Senior Robotics Engineer, Task Planning & Autonomy on a full-time basis. This is a role based in Chicago, Illinois, US.

Company
Edison Smart®
Location
Chicago, Illinois, US
Job type
Full-time
Pay listed
$180,000
Posted
Nov 1, 2026

Who this role suits

The listing does not state a required experience level here. Read the requirements in the description below and apply if they match your background.

How to prepare your application

  • Match your résumé to the requirements in the description, using the same wording where it is honest to do so.
  • Prepare a short example for each requirement you meet, and be ready to explain any you only partly meet.
  • Read what Edison Smart® publishes about its product or team, so you can say clearly why this role and this company.

Apply only on Edison Smart®'s own site. A genuine employer never asks candidates for money, deposits or bank details to apply, interview or “secure” a job. If something looks wrong, use Report a problem with this listing and we will review it. Read how we check listings.

About the role

Senior Robotics Engineer, Task Planning & Autonomy

Chicago, IL - On site

Up to $180k + equity

Visa sponsorship and relocation support

The company

A well funded construction robotics company building AI powered robots that manufacture.

The role

You’ll own how the robots decide what to do next. A planning layer already exists; your job is to make it scalable, production ready and able to work across both robot product lines.

Every robot action comes down to two primitives: move or actuate. You’ll build the planner that reasons over a goal, sequences those primitives, picks classical control or a learned policy for each step, and recovers when something goes wrong. The aim is simple: a robot finishes a whole panel or room on its own.

This is the first of three principal level hires (alongside Robot Learning and World Sensing), so you’ll be shaping the foundation the rest of the autonomy stack is built on.

What you’ll do

  • Define the primitive library and the contract between planner and executor
  • Build the task graph from BIM models: what’s in front of the robot and what depends on what
  • Build a two layer planner: a reasoning layer (LLM / reasoning models) for open ended decisions, plus solvers for reach, collision and trajectory
  • Decide where reasoning models help and where they don’t, and keep them off the real time control path
  • Build execution monitoring and recovery: verify, retry, switch approach, flag or escalate to a person
  • Log every decision with its reasoning so any outcome can be explained
  • Design for two robots sharing one task (one holds, one fastens)
  • Set autonomy architecture, mentor engineers, and still write production code and test on real robots every week

What you’ll bring

  • 5+ years building autonomy, task planning or decision making systems for robots or AVs, deployed in production
  • Hands on manipulation experience with real hardware, ideally end effectors in unstructured environments
  • Task level planning: behavior trees, TAMP, HTN or similar
  • Execution monitoring and fault recovery on a deployed system
  • Hands on with LLMs or reasoning models in a robot decision loop
  • Strong Python and C++, ROS2, Linux, Docker, CI/CD
  • Real ownership: you built it, not just contributed to it. Startup or small team experience is a big plus
  • Experience setting technical direction and mentoring senior engineers

Nice to have

  • MS or PhD in Robotics, CS or AI
  • Navigation as well as manipulation
  • MoveIt, OMPL or trajectory optimisation
  • Multi robot coordination or fleet orchestration
  • Functional safety or formal verification
  • CAD / BIM experience, or a background in construction, manufacturing or industrial automation

What’s on offer

  • Base salary up to $200k
  • Equity
  • Comprehensive benefits
  • Visa sponsorship and relocation support
  • Direct access to robots, sensors and manufacturing environments every week
  • A rare problem: agentic planning on physical robots, in messy real world sites