Location Name: Pune Corporate Office - Mantri
Job Purpose
We are seeking a dynamic AI Engineer to join our pioneering Conversational Text AI team. The ideal candidate will possess a strong foundation in model development, UI development and development of APIs, multi-system integrations. You will be involved in end-to-end stage of development life cycle.
Duties And Responsibilities
Deliveries with respect to Conversational Text AI Platform:
- Build and maintain Conversational Text AI system using state-of-the-art LLM frameworks.
- Collaborate with product owners and domain experts to build reusable components for business process.
- Develop core infrastructure and reusable components to support the deployment of conversational AI systems.
- Work on orchestration, prompt engineering, and LLM-powered integrations.
- Implement scalable solutions integrated with respective echo systems and enterprise data platforms.
- Contribute to the design of modular, extensible, enterprise-grade architectures.
- Fine-tune & optimization for speed, accuracy, performance and maintainability across business units.
- Contribute to CI/CD automation and maintain operational stability of application services.
Generative AI & Model Optimization
- Fine-tune LLMs/SLMs with proprietary NBFC data.
- Perform distillation, quantization of LLMs for edge deployment.
- Evaluate and run LLM/SLM models on local/edge server machines.
Self-Learning Frameworks
- Build self-learning systems that adapt without full retraining (e.g., learn new rejection patterns from calls).
- Implement lightweight local models to enable real-time learning on the edge.
Key Decisions / Dimensions
Platform Design & Delivery, Model Selection, Customization (if any) & Testing:
- Choosing the right model for various task and actions.
- Selecting appropriate model so that tasks can complete in efficient manner.
- Defining reusable components in the platform. Delivery using configuration approach should be first preference, in case that does not work should go for customization.
- Defining configuration parameters and incorporate them as platform design.
- Testing and end to end testing of the project deliverable.
- Load balancing between different models.
- Always have switch on/switch off feature.
- Must have all services backed up on primary/HA & DR servers.
Prompt Engineering
- Prompt Design & Development: Crafting prompts that guide AI systems to produce desired outputs for various applications, such as text generation, translation, question answering, and creative writing.
- Testing and Evaluation: Analysing the effectiveness of prompts and refining them based on results to ensure accurate and relevant responses.
- Bias Mitigation: Designing prompts that minimize bias and ensure fair and equitable outcomes from AI systems.
Major Challenges
- Support from other platform owners
- Building a Conversational Text AI BOT that doesn't just answer but negotiates with human-like reasoning.
- Running large AI models in low-latency, low-bandwidth environments without cloud dependency.
- Getting the end-to-end domain knowledge
- Managing data and information security of the application.
Educational Qualifications
Required Qualifications and Experience
- Educational Background: Bachelor's or Master's degree in computer science, Engineering, or a related field.
- Experience: 4–7 years of experience in AI/ML, with exposure to Python, Node.JS, JavaScript, HTML/CSS, Redis, Postgres, Azure COSMOS, DevOps, CI/CD.
- Strong programming skills in languages such as Python, Node.JS, JavaScript, HTML/CSS.
- Familiarity with Redis, Postgres, Vector Embeddings, Speech-to-Text & Text-to-Speech Services, Azure COSMOS, DevOps, CI/CD, Lang-Chain or Lang-Graph.
- Experience building with or integrating LLMs for task automation, reasoning, or autonomous workflows
- Strong understanding of prompt engineering, tool calling, and agent orchestration.
