Software Development Engineer 2

Software Development Engineer-2 (SDE-2)

Location: Gurgaon

Experience: 1-2 years

Role Overview

The Software Development Engineer-2 (SDE-2) is responsible for designing, building, and deploying large-scale, high-performance machine learning solutions for production environments. The role emphasizes strong computer science fundamentals, deep learning model development, and high-performance inference engineering.

The engineer will work on end-to-end ML pipelines, optimize inference systems for low latency and high throughput, and integrate models into distributed, production-grade systems. The role also focuses on system efficiency, security, compliance, and close collaboration with cross-functional teams to convert research models into scalable production applications.

Key Responsibilities

End-to-End ML Pipeline Development

• Design, build, and optimize model training, evaluation, and deployment pipelines
• Ensure pipelines are scalable, reliable, and production-ready
• Support continuous improvement of ML workflows for faster development cycles

High-Performance Inference Engineering

• Architect and scale distributed inference systems
• Handle large request volumes with minimal latency
• Optimize compute utilization while maintaining system stability

Model Optimization & Tuning

• Apply model optimization techniques such as:
• Quantization
• Pruning
• ONNX / TensorRT acceleration
• GPU-level optimizations
• Improve real-time inference performance and system efficiency

Data Engineering & Processing

• Develop robust data ingestion and preprocessing pipelines
• Handle structured, unstructured, and multimodal datasets
• Ensure data quality, integrity, and consistency across ML workflows

Key Performance Indicators (KPIs)

Model Deployment & Performance

• Reduction in inference latency
• Lower compute cost and memory footprint
• Successful deployment of ML models meeting defined SLAs (throughput, latency)

Pipeline Reliability & Efficiency

• High uptime, scalability, and stability of ML services
• Faster development cycles through optimized pipelines and tooling

Education & Experience

• Bachelors or Master’s degree in Computer Science, Engineering, or related field
• 1–2 years of experience designing and deploying ML systems in production environments

Technical Skills Required

Core Skills

• Strong fundamentals in:
• Computer architecture
• Operating system internals
• System design
• Experience designing and maintaining scalable API-based systems

Programming & Frameworks

• Python with deep learning frameworks (PyTorch, TensorFlow)
• System-level programming experience (C++ preferred)
• Experience building high-performance APIs (FastAPI)

ML & AI (Preferred)

• Knowledge of Computer Vision and NLP frameworks:
• OpenCV
• HuggingFace Transformers

MLOps & Infrastructure (Preferred)

• Familiarity with:
• MLflow
• Kubeflow
• Airflow
• Docker
• Kubernetes