Description

We embrace a talent-led culture where success is defined by technical ingenuity and creative exploration. In this role, you will not simply consume standard APIs—you will architect, prototype, and scale groundbreaking Generative AI capabilities that have never been built before in construction ERP. Working out of our Chennai engineering hub alongside some of the sharpest minds in software development, data science, and product design, you will possess end-to-end technical autonomy to take AI features from initial zero-shot experimentation all the way to global production releases.
 

Key Exciting Responsibilities
 

• AI Architecture & End-to-End Delivery: Design, develop, and deploy production-ready AI solutions across our ERP platform ecosystem, managing the full development lifecycle from exploratory prototyping to enterprise-scale deployment.
• LLM Engineering & Framework Integration: Build robust Generative AI workflows utilizing LangChain, Azure OpenAI, and foundational LLMs, integrating vector search databases to ground AI outputs in proprietary enterprise data.
• Advanced Prompt & Context Engineering: Engineer complex multi-step prompts and optimize zero-shot and few-shot techniques to power personalized recommendations, intelligent document processing, and natural language workflows.
• Model Evaluation & Hyperparameter Tuning: Rigorously evaluate LLM performance, fine-tune model parameters, optimize latency and token economics, and establish interpretability standards for reliable web application integrations.
• Cross-Functional Product Roadmap Influence: Collaborate closely with product managers, UX designers, and integration engineers to identify high-value customer problems and translate them into AI-driven product capabilities.
• Continuous Technology Exploration: Stay ahead of the curve across rapidly emerging AI/ML breakthroughs, agentic frameworks, and new model iterations, evaluating their application within enterprise construction workflows.
   

Essential Skills & Experience
 

• Professional Experience: 6+ years of dedicated professional experience in Machine Learning and AI engineering, with a proven track record of architecting, deploying, and maintaining production-grade AI solutions.
• Core Technical Stack: Direct hands-on expertise with Azure OpenAI, OpenAI Studio, and state-of-the-art LLMs (GPT-4/GPT-4o and next-generation iterations).
• AI Frameworks & Tooling: Deep proficiency in LangChain, modern LLM orchestration layers, and working with both NoSQL platforms and dedicated Vector Databases (e.g., Pinecone, Milvus, Qdrant, Chroma).
• Programming & Software Engineering: Strong fluency in Python, supported by solid computer science fundamentals in data structures, algorithms, system design, and clean-code engineering practices.
• NLP & Generative AI Mastery: In-depth understanding of natural language processing (NLP), deep learning fundamentals, and generative architectures (such as GPT, VAEs, and GANs).
• Evaluation & Alignment: Demonstrated ability to evaluate response quality, reduce hallucinations, and optimize context retrieval to deliver reliable, enterprise-grade user experiences.
   

Bonus Points For:
 

• Prior experience implementing AI/ML or automation features inside enterprise ERP, accounting, or supply chain platforms.
• Hands-on familiarity with Retrieval-Augmented Generation (RAG) production architectures and agentic workflows.
• Familiarity with Microsoft Azure cloud infrastructure, containerized deployments (Docker/Kubernetes), and continuous integration pipelines for ML systems

Key Skills

Education

Any Graduate