Datayaan Solutions Private Limited
Job Description
AI Engineer
LLM Applications | RAG & Semantic Search | AI Workflow Engineering
Position AI Engineer
Location Chennai, India
Experience 5 – 10 Years
Working Model Agile (Scrum)
Role Summary
We are looking for an experienced AI Engineer to design and build AI-powered features for our enterprise platform using Large Language Models (LLMs). The role involves implementing Retrieval-Augmented Generation (RAG) and semantic search solutions, designing prompt orchestration and AI workflow logic, and integrating AI capabilities responsibly into enterprise applications within an Agile delivery model.
Key Responsibilities
- Develop AI-powered application features using Large Language Models (LLMs).
- Implement Retrieval-Augmented Generation (RAG) solutions, semantic search, and knowledge retrieval capabilities.
- Design prompt orchestration, context management, and AI workflow logic.
- Integrate AI tools, external services, and agent-based workflows into enterprise applications.
- Contribute to the implementation of AI governance, guardrails, and responsible AI practices.
- Evaluate and adopt emerging AI frameworks, technologies, and engineering approaches.
- Build and maintain embedding pipelines and vector database integrations for semantic search.
- Collaborate with backend and front-end engineering teams to embed AI capabilities into platform components.
- Document AI solution architecture, prompt libraries, and evaluation approaches.
- Participate actively in Agile/Scrum ceremonies and contribute to sprint planning and technical design.
Required Skills & Experience
- 5–10 years of overall software engineering experience, including meaningful hands-on experience building LLM-based application features.
- Strong programming skills in Python and/or Java.
- Hands-on experience with LLM APIs (OpenAI, Anthropic Claude, Azure OpenAI, or similar) and frameworks such as LangChain, LlamaIndex, or Semantic Kernel.
- Practical experience implementing RAG pipelines, embeddings, and semantic search using vector databases (e.g., Pinecone, Weaviate, FAISS, pgvector).
- Experience with prompt engineering, prompt orchestration, and context/session management.
- Familiarity with agent-based or multi-agent workflow frameworks (e.g., LangGraph, AutoGen, CrewAI).
- Understanding of AI governance, guardrails, content safety, and responsible AI practices.
- Experience integrating AI capabilities into enterprise applications via APIs and microservices.
- Comfortable working within an Agile/Scrum delivery model.
Good to Have
- Experience with model evaluation, fine-tuning, or MLOps practices.
- Exposure to Fintech, Straight-Through Processing, or Modern Data Stack domains.
- Working knowledge of cloud AI services (AWS Bedrock, Azure AI Foundry, GCP Vertex AI).
- Familiarity with Kafka or event-driven integration patterns.
Educational Qualification
Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Data Science, Engineering, or a related field (or equivalent practical experience).
Work Location: In person
