Generative AI Engineer (Backend & REST API Focus)
Location : Chennai, India- Hybrid | Employment Type : Full Time
Why This Role Is Unique
This is not just another AI role. Sixty percent of your work will focus on REST API design, microservices architecture, and enterprise-grade backend engineering, while the remaining 40% will let you push boundaries with Generative AI, LLMs, and advanced prompt engineering.
You will not just build modelsyou will build production-ready, AI-driven platforms for enterprise clients.
Key Responsibilities :
Backend & API Engineering (60% Focus) :
- Design and implement REST APIs and microservices for high-performance AI systems.
- Apply enterprise object-oriented programming best practices for secure, scalable backend services.
- Integrate AI-powered features with cloud-native architectures.
- Generative AI & LLM Development (40% Focus)
- Build LLM-powered features with the OpenAI API or other LLM APIs (reasoning and non-reasoning models, temperature tuning, version control).
- Implement retrieval-augmented generation (RAG).
- Apply advanced prompt engineering and model tuning techniques for optimized results.
- Deploy and manage solutions using Docker and secure integrations (e.g., SSO, Google Drive).
What Were Looking For :
10+ years of backend engineering experience (REST APIs, microservices, OO enterprise architecture).3+ years of experience building AI / ML solutions (LLMs, RAG, OpenAI API).Strong hands-on Python expertise and object-oriented design patterns.Hands-on experience with Langchain, Lambda, Docker, and secure system integrations.Proven track record delivering production-ready, scalable applications.Nice-to-Have Skills :
MLOps, vector databases, or additional AI frameworks.Cloud-native deployment experience (AWS, Azure, or GCP).Previous experience in healthcare or regulated environments.(ref : hirist.tech)