Job
Description
As a Platform Engineer at our company, you will have the exciting opportunity to work on cutting-edge AI technologies and be a key contributor to the development of intelligent applications powered by Generative AI. You will be an essential part of a platform team, responsible for creating innovative solutions that are both functional and intelligent. **Core Responsibilities:** - **AI-Powered Product Development:** - Create and enhance key products such as: - Intelligent chatbots for customer service and internal support. - Automated quality analysis and call auditing systems using Large Language Models (LLMs) for transcription and sentiment analysis. - AI-driven internal portals and dashboards to surface insights and streamline workflows. - **Full-Stack Engineering:** - Write clean, scalable, and robust code across the MERN stack (MongoDB, Express.js, React, Node.js) and Python. - **Gen AI Integration & Optimization:** - Work hands-on with foundation LLMs, fine-tuning custom models, and implementing advanced prompting techniques (zero-shot, few-shot) to solve specific business problems. - **Research & Prototyping:** - Explore and implement cutting-edge AI techniques, including setting up systems for offline LLM inference to ensure privacy and performance. - **Collaboration:** - Partner closely with product managers, designers, and business stakeholders to transform ideas into tangible, high-impact technical solutions. **Skills & Experience:** - **Experience:** - 2 to 5 years of professional experience in a software engineering role. - **Full-Stack Proficiency:** - Strong command of the MERN stack (MongoDB, Express.js, React, Node.js) for building modern web applications. - **Python Expertise:** - Solid programming skills in Python, especially for backend services and AI/ML. - **AI & LLM Experience (Must-Have):** - Demonstrable experience integrating with foundation LLMs (e.g., OpenAI API, Llama, Mistral, etc.). - Hands-on experience building complex AI systems and implementing architectures such as Retrieval-Augmented Generation (RAG) to ground models with external knowledge. - Practical experience with AI application frameworks like LangChain and LangGraph to create agentic, multi-step workflows. - Deep understanding of prompt engineering techniques (zero-shot, few-shot prompting). - Experience or strong theoretical understanding of fine-tuning custom models for specific domains. - Familiarity with concepts or practical experience in deploying LLMs for offline inference. - **R&D Mindset:** - A natural curiosity and passion for learning, experimenting with new technologies, and solving problems in novel ways. **Points (Nice-to-Haves):** - **Cloud Knowledge:** - Hands-on experience with AWS services (e.g., EC2, S3, Lambda, SageMaker). You have a unique opportunity to be part of a team that values creativity, innovation, and continuous learning. If you are passionate about AI technologies and enjoy tackling complex technical challenges, this role is tailor-made for you.,
