Platform Engineer

About the Role

We are seeking a highly motivated and creative Platform Engineer with a true research mindset. This is a unique opportunity to move beyond traditional development and step into a role where you will ideate, prototype, and build production-grade applications powered by Generative AI.

Core Responsibilities

• Innovate and Build:

  Design, develop, and deploy full-stack platform applications integrated with Generative AI, from concept to production.

• 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 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.

Required Skills & Experience

• Experience:

  2-5 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 workloads.

• Generative 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.

Bonus Points (Nice-to-Haves)

• Cloud Knowledge:

  Hands-on experience with

  AWS

  services (e.g., EC2, S3, Lambda, SageMaker).