Description
Senior Machine Learning Engineer | On-Site Indianapolis | Ag-Tech
Industry – Agriculture
Description
We are working alongside an agriculture analytics company turning multi-source data, including aerial imagery and complex datasets into actionable insights for growers.
We’re hiring a Senior Machine Learning Engineer with 5+ years of experience to lead the implementation, integration, and maintenance of our ML/CV pipelines for Analytics products. You will build production-grade systems, own automated large-scale testing pipelines, ensure pipeline reliability, and shape technical direction. This role requires hands-on engineering and leadership skills, including mentoring, improving code quality, and representing ML in cross‑functional discussions.
The client
Our client are an established Ag-Tech company, providing growers insights and agronomic data which allow them to increase their yields and reduce costs
Location
Indianapolis - Hybrid 3 Days On Site
Key Responsibilities
- Design, develop, maintain, and integrate end‑to‑end ML/CV pipelines for Analytics (ingestion → preprocessing → training → evaluation → deployment).
- Build and own automated large‑scale testing pipelines with quality gates and performance dashboards.
- Lead larger ML projects and deliver production-grade solutions with clear milestones, risks, and documentation.
- Collaborate with researchers to productionize segmentation and multimodal deep learning models.
- Own and maintain ML pipelines using ClearML (experiment tracking, orchestration, model registry).
- Manage annotation workflows and feedback loops between labeling, training, and evaluation.
- Scale distributed training on AWS GPU clusters; optimize cost/performance.
- Deploy optimized models for inference at scale using NVIDIA Triton Inference Server.
- Implement MLOps best practices: CI/CD, containerization, model versioning, monitoring, and alerting.
- Optimize models for cloud deployment.
- Support geospatial/remote sensing data pipelines for training and inference at scale.
- Define SLAs, build runbooks, and establish observability for pipelines (data quality, drift, latency, throughput).
- Mentor junior/mid-level engineers; perform code and design reviews; improve architecture for scalability and reliability.
- Represent ML in cross‑functional meetings (Product, Imaging/AO, Backend, QA) and contribute to technical roadmaps.
Requirements/Qualifications:
- Master’s degree in Computer Science, Engineering, or related field.
- 5+ years of hands‑on ML/DL engineering experience (production).
- Strong expertise with PyTorch (PyTorch Lightning is a plus).
- Proven experience with ClearML for orchestration, experiment management, and model lifecycle.
- Experience deploying/training on AWS GPU (ECS/EKS or EC2).
- Proficiency with Docker and container orchestration (Kubernetes preferred).
- Experience with NVIDIA Triton Inference Server for high‑throughput serving.
- Solid MLOps background: versioning, monitoring, CI/CD, reproducibility.
- Strong Python engineering skills focused on scalability and reliability.
- Familiarity with large‑scale imagery or multimodal datasets.
Preferred, not necessary qualifications
- Remote sensing pipelines (GDAL, Rasterio, GeoPandas).
- Distributed training frameworks (DDP, Horovod, Ray).
- Infrastructure‑as‑code (Terraform, CloudFormation).
Why join our client?
- Lead deep learning systems that combine imagery with complex real‑world datasets across millions of acres.
- Own the journey from notebook → reliable production service, impacting accuracy, stability, and cost.
- Work onsite with a strong engineering team in Yerevan and collaborate daily with global counterparts.
- Contribute strategically to product roadmaps and shape the future of agricultural AI.
