About this role
DigitalXNode is hiring a full-time AI Engineer for Bangalore or Hyderabad to design, build and deploy secure, scalable Generative AI applications and intelligent systems for business automation and enterprise products. The role combines LLM applications, retrieval-augmented generation (RAG) and autonomous, multi-agent workflows, with an emphasis on production deployment rather than experimentation.
Responsibilities
- Develop enterprise-grade Generative AI applications, autonomous agents and RAG pipelines using vector databases. Integrate LLMs through APIs and open-source frameworks, and build workflows that improve business processes and operational efficiency.
- Optimize prompts, workflows and model performance; evaluate models through testing and benchmarking; and implement guardrails, safety mechanisms and responsible AI practices.
- Monitor deployed systems and improve their accuracy, reliability and scalability. Work with product managers, software engineers and AI researchers to integrate AI capabilities into products and assess emerging technologies.
Required expertise:
- Generative AI, agentic AI, LLMs, prompt engineering, workflow orchestration, multi-agent systems, RAG and AI automation; Python, REST APIs, object-oriented programming and software engineering practices.
- Experience with one or more of LangChain, LangGraph, LlamaIndex, CrewAI or AutoGen; hands-on experience with OpenAI, Anthropic Claude, Google Gemini or open-source LLMs such as Llama, Mistral and DeepSeek.
- Vector databases and search technologies including Pinecone, Weaviate, ChromaDB or FAISS; experience with AWS, Microsoft Azure or Google Cloud Platform. Deployment skills include Docker, CI/CD pipelines, Git and GitHub.
Preferred qualifications
- 5–8 years of software engineering experience; substantial hands-on experience with Generative AI and LLM applications; scalable AI architecture, evaluation metrics and benchmarking, vector search and semantic retrieval, responsible AI and governance, and Agile development experience.
- Strong analytical, problem-solving, communication and collaboration skills. Semantic Kernel, Elasticsearch and Kubernetes are specifically marked preferred.
The posting mentions work on enterprise AI projects for global clients, continuous learning and career development, and competitive compensation and benefits; it does not specify a salary.