Hitesh Garg

Software Engineer

Gurugram, Haryana, India9 yrs 2 mos experience

Key Highlights

Expert in building scalable backend architectures.
Proficient in Python and AWS cloud services.
Strong mentor with a focus on best coding practices.

Stackforce AI infers this person is a Backend Software Engineer specializing in AI/ML applications.

Contact

Skills

Core Skills

PythonDatabase Management

Other Skills

API DevelopmentAgile Software DevelopmentAmazon Web Services (AWS)Analytical SkillsAttention to DetailBack-End Web DevelopmentCode ReviewCode profilingCommunicationCompetitive ProgrammingDatabasesDebugging CodeDeep LearningDjangoDjango REST Framework

About

As a seasoned Software Engineer with expertise in Python web dev ecosystem, I specialize in building scalable, high-performance backend architectures and driving automation processes. With extensive experience across AWS cloud services, I engineer robust, efficient systems that optimize workflow and enhance user experiences. Throughout my career, I have demonstrated a strong aptitude for developing and maintaining RESTful APIs, refining database queries for performance improvements, and mentoring teams to adhere to best coding practices. I excel in collaborative environments, consistently delivering solutions that meet both business and technical needs. Driven by a passion for technology and a commitment to excellence, I am always exploring new ways to innovate and contribute to the success of my team and organization. Let's connect and explore how we can work together to build scalable and secure applications.

Experience

Epam systems

Lead Software Engineer

May 2025 – Present · 10 mos · Gurugram, Haryana, India · Remote

Project: Face Detection and Recognition Platform
Developed a robust Python-based pipeline for automated face detection, embedding extraction, and metadata ingestion from large image datasets.
Integrated state-of-the-art deep learning models (InsightFace/AuraFace) for high-accuracy face recognition and feature extraction.
Designed and implemented a scalable database schema in PostgreSQL to store facial embeddings and associated metadata for efficient search and retrieval.
Ensured compatibility with both local and cloud (AKS/Docker) deployments, including secure environment setup and configuration management.
Leveraged cosine similarity for efficient and scalable comparison of high-dimensional feature vectors, enabling robust face identification and verification.
Improved search accuracy and relevance, resulting in >95% precision for face identification tasks.
Enabled sub-second retrieval of top-N similar faces from a database of 100,000+ images.