Founding Engineer · Pune

Who we are

We're building S18LabX, an early-stage sports-tech startup in Pune focused on sports video intelligence and AI-assisted coaching. Founded by Arjun Shah (Columbia MBA; previously at Nanonets, Credit Suisse and Barclays) and Chirag Lulla (entrepreneur and sports team owner), we aim to turn training footage into information players, coaches, and parents can use.

A coach can watch a training session and understand each action: the setup, movement, contact, outcomes, and patterns. We want AI to do the same from ordinary phone footage, despite real-world variability.

We're looking for a Founding Engineer with a strong AI/computer vision background to help shape and build our technical foundation alongside the team.

This is not a role where you'll be handed a defined ML problem and asked to implement it. You'll help determine what to build, which technical approaches actually work, what data we need, how to evaluate success, and how to turn an experimental system into a product coaches use every day.

Responsibilities

• Shape and build the video/ML stack with the team, from ingestion to inference and structured player and action data
• Develop models for tracking, action segmentation, movement, contact, outcomes, and other key events in training video
• Design data collection, labelling, and dataset workflows that turn coach corrections into useful training data
• Build evaluation datasets and benchmarks, analyse failures, and test performance on unseen training sessions
• Work with the team to turn model outputs into observations and feedback coaches can review
• Design scalable, cost-efficient pipelines, balancing accuracy, latency, compute cost, engineering complexity, and product value
• Work with the founders and engineers to shape the product, architecture, roadmap, and experiments
• Help hire and build the engineering team
• Own significant parts of the stack and move quickly from idea → experiment → working product → iteration

The loop you'll help build and improve

Video → AI analysis → Coach correction → Proprietary labelled data → Better models → Better product

What we're looking for

Must have

• Strong ML / computer vision fundamentals and hands-on experience building, training, and debugging models in Python and PyTorch, OpenCV, TensorFlow
• Experience building and shipping computer vision, video ML, or related machine learning systems, taking models beyond a notebook into usable software with reliable, maintainable inference pipelines
• Strong understanding of one or more areas such as object detection, tracking, pose estimation, action recognition, temporal modelling, or video understanding
• Comfortable working with messy, noisy, real-world data and limited or expensive labelled datasets, including assessing label quality, identifying data gaps, and making effective use of available training data
• Experience building evaluation datasets and benchmarks, selecting meaningful metrics, testing on unseen data, and analysing failures to guide model improvements, data collection, and further experiments

Nice to have

• Experience with video processing and inference tools such as FFmpeg, YOLO, ONNX
• Experience building ML data and labelling pipelines, or deploying ML systems at scale
• Broader software engineering experience with backend systems, infrastructure, or application development
• Interest or experience in sports, biomechanics, or sports analytics

You do not need to have worked in sports before. We care more about your ability to reason about unfamiliar problems and build systems that work in the real world.

The kind of person who will thrive here

This is a founding role, not a narrowly scoped engineering position.

You should be comfortable taking ownership with incomplete information, an evolving architecture, and no established playbook. Bring strong experimental instincts: form a hypothesis, test it quickly, measure the results, and decide what to pursue or abandon.

One week you might be testing a video model. The next, figuring out how to label thousands of training clips or build a reliable inference pipeline.

You'll help shape the technical direction of the company and the product itself, working alongside the founders and engineering team.

This is not a pure research role. We care about technical rigour and experimentation, alongside a strong bias toward shipping something coaches use, learning from real users, and continuously making it better.

Role

• Founding-team engineering role with shared technical ownership
• Initially in person in Pune, with relocation expected; hybrid/remote arrangements may be considered later
• Full-time preferred, open to an initial contract / trial period for the right person
• Cash compensation + meaningful equity