Position Overview
We are looking for a senior backend software engineer to join machine learning platform engineering team. In this role, you will be responsible for the development and expansion of core infrastructure supporting company’s AI/ML products. You will partner closely with data scientists and machine learning engineers to design and deliver state-of-the-art AI/ML infrastructure, with a strong focus on deploying and productionizing models across multi-cloud and hybrid environments. The contract offering the opportunity to continually challenge yourself, expand your skillset, own your work.
What You Will Do
- Technical Contributions: Design, develop, test, and release software and infrastructure supporting AI/ML and experimentation workflows.
- Model Deployment & Productionization: Design, develop, and deploy ML models into production across AWS, GCP, Azure, and on-prem environments.
- Scalable Pipelines: Build scalable, high-throughput ML pipelines supporting multi-GPU and distributed training/inference.
- Infrastructure & Deployment: Implement robust deployment strategies using Docker, Kubernetes, Terraform, and CI/CD workflows. Deploy services into AWS and Kubernetes environments and participate in an on-call rotation.
- Optimization: Optimize model serving for LLMs and Generative AI applications, ensuring low latency and high availability. Apply model inference optimization, GPU acceleration, and parallel processing techniques.
- Collaboration: Work closely with data scientists, MLOps, platform engineering teams, and product managers to operationalize models and become a valued member of an autonomous, cross-functional team.
- Monitoring & Best Practices: Ensure monitoring, observability, and performance tuning of deployed models at scale. Drive best practices in model versioning, reproducibility, and compliance (including security and data governance).
- Code Review & Documentation: Grow our knowledgebase by participating in code reviews, writing, and reviewing documentation.
- Architecture & Process Improvement: Contribute to architecture decisions, tool evaluation, and process improvements for ML deployment and serving.
- Professional Development: Stay up-to-date on the latest technologies and pro-actively identify opportunities for growth.
Qualifications
Required:
- 5+ years of experience in a fast-paced technical, problem-solving environment as a software or machine learning engineer, with a focus on model deployment and productionization.
- Proficient in Python (mandatory); experience with Java is a plus.
- Demonstrable understanding of software engineering fundamentals related to security, scalability, asynchronous programming, and transactions.
- Knowledge and demonstrated experience developing with Terraform for AWS and deploying infrastructure as code (IaC).
- Proven experience with LLMs, GenAI models, and distributed model serving.
- Deep understanding of multi-cloud environments (AWS, GCP, Azure) and hybrid deployments.
- Experience with containerization (Docker) and orchestration (Kubernetes) for ML workloads.
- Strong knowledge of model inference optimization, GPU acceleration, and parallel processing.
- Familiarity with tools like TensorFlow Serving, TorchServe, Triton Inference Server, ONNX Runtime, or similar.
- Experience in high-throughput system design, REST/gRPC APIs for model serving, and scaling strategies.
- Solid grasp of MLOps concepts including CI/CD, monitoring, drift detection, and retraining workflows.
- Experience with relational and/or NoSQL databases, understanding of normalization/denormalization, constraints, transactions, replication, and sharding.
- Attention to detail, good work ethic, ability to work on multiple projects simultaneously, and strong communication skills.
