ApplySarthi

Prediction Engineer

Cat

Tailor my CV for this job, freeView job and applyYour CV rewritten for this role, from your real experience. Sign in with Google, nothing to install.

Got this interview? Our apps help you get the job.

Skills named in this job

Read from the description itself, not inferred.

This role on the market

12 open prediction roles across 10 companies are on ApplySarthi right now.

What prediction roles keep asking for: Python (50%), C++ (42%), Machine learning (42%), Deep learning (33%), PyTorch (25%), Product management (17%), R (17%), TensorFlow (17%) — counted across their open postings here.

C++ jobs

Cat has 1,238 open roles listed here.

Counted across 14 company job boards, updated as roles open and close.

Preparing for this interview

Interviews for prediction roles keep coming back to Python, C++, Machine learning, Deep learning. Practise those questions before you sit with Cat.

Questions you are likely to be asked

  1. Why do you want to join Cat?
  2. What is your experience with C++? Tell me one thing you learned the hard way.
  3. Describe a time a deadline forced a trade-off in quality. What did you choose and why?
  4. How would you design an API for a feature you have worked on?
  5. What do you do when a production issue happens on your code?

Prep Sarthi gives you a free mock interview: an AI interviewer asks you questions like these out loud, from your own CV and this job, and shows your score and your weakest answer.

Practise the Prediction Engineer at Cat interview free →

Career Area: Engineering Job Description: Your Work Shapes the World at Caterpillar Inc. When you join Caterpillar, you're joining a global team who cares not just about the work we do – but also about each other. We are the makers, problem solvers, and future world builders who are creating stronger, more sustainable communities. We don't just talk about progress and innovation here – we make it happen, with our customers, where we work and live. Together, we are building a better world, so we can all enjoy living in it. 高级感知预测工程师 负责矿山自动驾驶场景下目标行为理解、轨迹预测及地图约束预测算法研发,为决策规划模块提供高可靠预测结果,提升无人矿卡运行安全性与运输效率。 岗位职责 : 1. 预测模块从0到1框架建设 定义预测模块架构、输入输出、数据流和接口契约,明确与感知、融合跟踪、HD Map、决策规划和安全模块的协同关系。 建立目标状态建模、历史轨迹管理、行为意图识别、多模态轨迹预测、置信度输出和异常诊断流程。 设计可解释、可测试、可迭代的预测框架,支持交叉口、主路、装卸区、排队区、弱网及调度信息不完整等场景扩展。 2. 矿山混行混编预测算法开发 面向无人矿卡、人工矿卡、辅助车辆、挖机、装载机、洒水车、行人等对象建立行为和运动模型。 开发跟车、会车、切入切出、让行、汇入、路口通行、装载/卸载区车辆入换和排队等场景的意图识别与轨迹预测能力。 结合 HD Map、路网拓扑、作业区语义、路权/调度信息,生成候选路线、时间占用、冲突概率和不确定性表达。 3. 数据闭环、评估与工程落地 与感知、预测、决策规划、安全和仿真团队协同,保证预测输出可直接用于碰撞检测、让行、跟车、绕障和速度规划。 建立场景挖掘、标签体系、指标体系、仿真回放、问题复现和实车验证闭环,持续提升复杂场景覆盖度和稳定性。 优化预测模块时延、资源占用、稳定性和部署流程,支持 ROS2/C++ 工程化集成、日志追踪和问题定位。 任职要求 : 硕士及以上学历,自动驾驶、机器人、人工智能、计算机、控制、车辆工程等相关专业。 5年以上自动驾驶、机器人或无人系统算法经验,具备 Prediction、Tracking、Behavior Understanding 或 Planning 相关项目经验。 具备从0到1搭建算法模块、定义接口、建立评估指标并推动持续迭代的经验。 熟悉 CV、CA、CTRV、CTRA、Kalman Filter、EKF、UKF、IMM 等运动预测和状态估计方法。 熟悉 LSTM、GRU、Transformer、GNN、LaneGCN、VectorNet、HiVT、MTR、Scene Transformer 等深度学习预测方法者优先。 具备多模态轨迹预测、行为/意图识别、交互建模、轨迹评分、不确定性建模和置信度校准经验。 理解 HD Map、路网拓扑、Map Matching、地图语义表达、路线关联和地图约束下的候选轨迹生成。 理解预测与决策规划耦合关系,能够将预测结果转化为可用于安全距离、冲突检测、让行/跟车/绕障的工程输入。 加分项: 有矿山、港口、园区、物流场、工程机械或复杂封闭场景无人驾驶项目经验。 有混行、混编、多车协同、V2X、云端调度协同或非合作车辆交互预测经验。 有数据闭环、自动标注、仿真评估、实车回放、模型部署和线上问题定位经验。 熟悉 Apollo、Autoware 或大规模自动驾驶平台 Prediction 模块者优先。 有非结构化道路、地图信息不完整或地图局部失效场景下的行为与轨迹预测经验,能够融合目标历史轨迹、交互关系及实时道路结构开展预测者优先。 Posting Dates: September 18, 2026 - October 30, 2026 Caterpillar is an Equal Opportunity Employer. Qualified applicants of any age are encouraged to apply Not ready to apply? Join our Talent Community .

Match this job to your CV

ApplySarthi scores your CV against this role, shows the skills you are missing, and writes a tailored version for the application.

Check my match →

Similar open roles

Need answers during your interview? Try Live Sarthi.

Live Sarthi, an Interview Sarthi app, shows answer suggestions during the call.

Try Live Sarthi free →

A Windows app, from the same team as ApplySarthi.

Listed on workday · posted 2026-10-20. ApplySarthi collects openings and links to application pages; the role is advertised by Cat, not by us.