Product Specialist
Bajaj Finserv · Pune Division, Maharashtra, India
This listing has closed — view similar roles below.
- On site
- Full-time
- ₹900,000 / year
- Pune Division, Maharashtra, India
Job highlights
- Build autonomous AI agents with LLM frameworks.
- Develop reusable components for business automation.
- Optimize LLMs and manage AI model deployment.
- Design and implement self-learning AI systems.
- Experience with data platforms and AI tools.
About the role
AI Engineer Agentic AI
We are seeking a dynamic AI Engineer to join our pioneering Agentic AI team. The ideal candidate will possess a strong foundation in delivering projects on both SaaS & PaaS based platforms, Prompt Engineering, UI development and development of APIs. You will be involved in end-to-end stage of development life cycle.
Duties And Responsibilities
Deliveries with respect to Agentic AI Platform:
- Build and maintain autonomous software agents using state-of-the-art LLM frameworks.
- Collaborate with product owners and domain experts to build reusable components for business process automation.
- Develop core infrastructure and reusable components to support the deployment of agent-based AI systems.
- Work on agent orchestration, prompt engineering, and LLM-powered integrations.
- Implement scalable solutions integrated with CRM systems and enterprise data platforms.
- Contribute to the design of modular, extensible, enterprise-grade architecture.
- Fine-tune and evaluate AI agents for speed, accuracy, performance and maintainability across business units.
- Contribute to CI/CD automation and maintain operational stability of agent services.
Generative AI & Model Optimization:
- Writing and Optimizing Prompts
- 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 agentic and autonomous actions.
- Selecting appropriate model so that Agents can complete the autonomous tasks 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
- Agents must learn from failed interactions
- Building a Agents 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 agentic application.
Required Qualifications And Experience
Qualifications:
- Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field.
Experience:
- 2–4 years of experience in Data Technologies like Data Lake, Fabric, Data bricks etc.
Work Experience:
- Strong understanding of prompt engineering, tool calling, and agent orchestration.
- Good understanding of Data Platforms Like Data Lake, Data Bricks & MS Fabric
- Must have good understanding of Microsoft Fabric Data Agents
- Understanding of Microsoft Copilot Studio, Power Automate, and Power BI
- Familiarity with the Agent Development Kit (ADK) and protocols like MCP & A2A
- Familiarity with LangChain, Semantic Kernel, CrewAI, or LangGraph.
Key skills/competency
- AI Engineer
- Agentic AI
- Prompt Engineering
- LLM Frameworks
- Generative AI
- Data Lake
- Data Bricks
- Microsoft Fabric
- LangChain
- Semantic Kernel
Skills & topics
- AI Engineer
- Agentic AI
- Prompt Engineering
- LLM
- Generative AI
- Data Lake
- Data Bricks
- Microsoft Fabric
- LangChain
- Semantic Kernel
- SaaS
- PaaS
- API Development
- Business Process Automation
- Machine Learning
- Artificial Intelligence
- Software Development
- Pune Jobs
- Technology Jobs
How to get hired
- Tailor your resume: Highlight your experience with LLM frameworks, prompt engineering, and data platforms like Data Lake, Data Bricks, and MS Fabric.
- Showcase your skills: Emphasize your understanding of agent orchestration, tool calling, and AI model optimization.
- Quantify your achievements: Provide specific examples of how you've improved AI agent performance or enabled business automation.
- Prepare for technical interviews: Be ready to discuss your experience with LangChain, Semantic Kernel, and Microsoft Copilot Studio.
- Research Bajaj Finserv: Understand their focus on AI and digital innovation to align your answers with their goals.
Technical preparation
Master LLM frameworks like LangChain, Semantic Kernel.,Practice prompt engineering for diverse AI applications.,Gain hands-on experience with Data Lake, Data Bricks, MS Fabric.,Understand agent orchestration and tool calling concepts.
Behavioral questions
Describe a complex AI project you led.,How do you handle ambiguity in AI development?,Tell me about a time you overcame a technical challenge.,How do you ensure AI fairness and mitigate bias?
Frequently asked questions
- What specific AI models or LLM frameworks are most relevant for this AI Engineer role at Bajaj Finserv?
- For this AI Engineer position at Bajaj Finserv, a strong understanding of state-of-the-art LLM frameworks is essential. Experience with models like those used in LangChain, Semantic Kernel, CrewAI, or LangGraph is highly beneficial. Familiarity with Microsoft's AI ecosystem, including Microsoft Fabric Data Agents, Microsoft Copilot Studio, Power Automate, and Power BI, is also a key requirement for developing and deploying agent-based AI systems.
- How important is prompt engineering experience for the AI Engineer role at Bajaj Finserv?
- Prompt engineering is a critical component of this AI Engineer role at Bajaj Finserv. You will be responsible for crafting, testing, and refining prompts to guide AI systems for various applications, ensuring accurate and relevant outputs. Experience in designing prompts that minimize bias and promote fair outcomes is also highly valued.
- What kind of data technologies experience is required for the AI Engineer position at Bajaj Finserv?
- The AI Engineer role at Bajaj Finserv requires 2-4 years of experience in Data Technologies. This includes a strong understanding of Data Lake, Data Bricks, and MS Fabric. Familiarity with data platforms and how to leverage them for AI model training and deployment is essential.
- Does Bajaj Finserv expect candidates for the AI Engineer role to have experience with SaaS and PaaS platforms?
- Yes, Bajaj Finserv is looking for an AI Engineer with a strong foundation in delivering projects on both SaaS (Software as a Service) and PaaS (Platform as a Service) based platforms. This indicates a need for experience in developing and deploying AI solutions within cloud-based environments.
- What are the major challenges mentioned for the AI Engineer role at Bajaj Finserv?
- The major challenges for this AI Engineer role at Bajaj Finserv include ensuring agents learn from failed interactions, building agents with human-like reasoning for negotiation, running large AI models efficiently in low-resource environments without cloud dependency, acquiring end-to-end domain knowledge, and managing data and information security for agentic applications.
- Is there an opportunity to work with self-learning frameworks in this AI Engineer job?
- Absolutely. A significant part of this AI Engineer role at Bajaj Finserv involves building self-learning systems that can adapt without full retraining. This includes implementing lightweight local models for real-time learning on the edge, which is a key aspect of developing advanced agentic AI.