Senior AI Full Stack Engineer

Senior AI Full Stack Engineer

Number of years of experience: 5 to 8 years

Location : Chennai, Vellore, Tamil Nadu, Bengaluru; You will require to come to Chennai once a month.

Remote based : Remote

Permanent full time

Core working hours: 5.00pm-10pm IST time

Starting date: (1 to 30 days of notice period)

We are looking for a visionary and Senior AI Full Stack Engineer to drive the development of the next-generation AI platforms. You will be responsible for leading the architectural direction, mentoring engineers, and shipping production-grade LLM applications.

1. Hands-On Development & Architecture

Fullstack Execution: Implement scalable features using React.js/Next.js for the frontend and Python (FastAPI) or Node.js for backend services.

AI Pipeline Orchestration: Build and optimize LLM pipelines, moving seamlessly from experimental notebooks to high-availability production environments.

System Design: Architect microservices and API frameworks that support high-concurrency AI workloads.

2. GenAI Specialization

Prompt Engineering: Develop advanced prompt frameworks and strategies to enhance model accuracy and reliability.

Evaluation & Optimization: Conduct rigorous model evaluations, performance tuning, and implement RAG (Retrieval-Augmented Generation) systems.

Infrastructure: Design and implement CI/CD pipelines specifically tailored for AI systems, ensuring automated testing of both code and model outputs.

Candidate requirements

Experience: 5+ years of software engineering experience, with at least 2+ years in a technical leadership role.

Frontend expert-level skills in React.js, Next.js, and TypeScript.

Backend strong experience in Python (FastAPI) and/or Node.js.

AI/ML Implementation: Proven track record of deploying LLM or GenAI applications in a production setting.

Cloud & DevOps: Solid knowledge of AWS (SageMaker, Lambda, ECS, S3), Docker, and Kubernetes.

Infrastructure as Code: Experience with Terraform, DuploCloud, and CI/CD tools like GitHub Actions.

Leadership: Ability to lead code reviews, mentor junior developers, and uphold elite engineering standards.

Experience with fine-tuning or training proprietary LLMs.

Familiarity with AI orchestration frameworks like LangChain or LlamaIndex.

Background in A/B testing, experimentation frameworks, or contributions to open-source AI projects.