We are seeking a visionary Generative AI Engineer / Prompt Engineer to rapidly integrate and optimize Large Language Models (LLMs) and other generative technologies into our core B2B SaaS product. You will be at the forefront of our innovation, designing the systems that enable our platform to understand, generate, and process complex enterprise documents and data at scale. This role requires a unique blend of core engineering skills, deep understanding of modern LLM architectures, and creative problem-solving.

Key Technical Responsibilities :

1. LLM Integration and Fine-Tuning :

- Model Selection : Evaluate and integrate the best-fit commercial and open-source LLMs (e.g., GPT models, Llama, Mistral) for specific enterprise use cases (e.g., automated report generation, contract summarization, advanced customer service bots).

- Fine-Tuning/RAG : Implement and manage advanced techniques like Retrieval-Augmented Generation (RAG) and model fine-tuning to ground the LLMs with proprietary enterprise data, ensuring accuracy and reducing hallucinations.

- Prompt Engineering : Design, test, and optimize sophisticated prompt chains and engineering frameworks to achieve high-quality, reliable, and consistent outputs from the models for client-facing features.

2. Production Deployment and Optimization :

- API Development : Build scalable, low-latency APIs and microservices around the LLMs, handling high-volume concurrent requests for enterprise use.

- Performance & Cost : Focus on minimizing token usage and optimizing model inference latency, which is critical for the economic viability and performance of a GenAI-powered SaaS product.

- Data Security : Implement rigorous security and privacy controls around the data used for RAG and fine-tuning, ensuring strict adherence to client data protection mandates.

3. Experimentation and Research :

- Agentic Systems : Explore and build initial prototypes for autonomous AI agents that can handle multi-step business processes within the client environment.

- Evaluation : Develop quantitative metrics and human-in-the-loop validation processes to rigorously evaluate the quality and business impact of generative outputs.

What You'll Bring (Mandatory Skills & Experience) :

- Educational Excellence : B.Tech/M.Tech in Computer Science or a related discipline from an IIT, NIT, BITS Pilani, or IIIT is mandatory.

- Experience : 3 - 6 years of experience, with recent, significant exposure to NLP, Deep Learning, and the practical application of LLMs in a product environment.

- Core Tools : Strong proficiency in Python, ML frameworks (PyTorch/TensorFlow), and experience with LLM APIs and libraries (e.g., Hugging Face, LangChain, LlamaIndex).

- Cloud & Deployment : Familiarity with deploying and scaling containerized services (Docker/Kubernetes) on a cloud platform (AWS/GCP) for inference.

- Problem Solving : A creative, results-oriented mindset focused on turning bleeding-edge research into reliable, enterprise-ready features.

Logistics and Compensation :

Location : This is a Hybrid Work / Work from Office Only position in Bangalore, Mumbai, or Gurgaon. No remote options are available.