We are looking for a hands-on GenAI / Agentic AI Engineer to develop and integrate AI-powered capabilities into enterprise applications.

The candidate will work on LLM integrations, RAG pipelines, AI agents, APIs, and production deployment.

The role is primarily focused on implementation and engineering execution.

The ideal candidate should be comfortable taking AI features from development through testing and deployment while following production engineering practices.

Key Responsibilities :

GenAI Application Development :

- Develop enterprise applications powered by LLMs and Generative AI.

- Integrate models such as GPT, Claude, Llama, Mistral, or equivalent models through APIs.

- Build prompt templates, prompt workflows, and structured LLM interactions.

- Develop RAG pipelines for enterprise knowledge and document-based applications.

- Implement embeddings, semantic search, retrieval, and context-management workflows.

- Build basic to moderately complex AI agents and tool-calling workflows.

Agentic AI Engineering :

- Develop multi-step agent workflows for enterprise use cases.

- Integrate agents with APIs, databases, enterprise tools, and external services.

- Implement tool calling, workflow orchestration, memory, and context handling.

- Test agent behavior and improve response quality and reliability.

- Work with frameworks such as LangChain, LlamaIndex, or equivalent technologies.

Backend & API Development :

- Develop production APIs and backend services using Python or JavaScript/TypeScript.

- Build microservices supporting AI applications and workflows.

- Integrate AI capabilities with enterprise applications and data sources.

- Implement authentication, authorization, validation, and API security.

Cloud & Production Engineering :

- Deploy AI applications on Azure, AWS, or GCP, with preference for Azure.

- Containerize applications using Docker.

- Work with Kubernetes and CI/CD pipelines.

- Implement logging, monitoring, and basic observability for AI workloads.

- Troubleshoot application and deployment issues.

AI Quality & Safety :

- Implement basic guardrails for AI applications.

- Monitor LLM outputs and identify quality or reliability issues.

- Work with evaluation approaches for prompts, RAG retrieval, and agent responses.

- Follow security, privacy, and Responsible AI practices.

Required Skills :

- Hands-on GenAI development.

- Agentic AI / AI agent development.

- Python or JavaScript/TypeScript.

- LLM API integration.

- RAG.

- Embeddings and vector search.

- LangChain / LlamaIndex or equivalent.

- Azure OpenAI or similar managed AI platforms.

- REST APIs and microservices.

- Docker.

- Kubernetes.

- CI/CD.

- Git.

Good to Have :

- Pinecone, FAISS, Chroma, or Azure AI Search.

- Redis.

- Kafka or event-driven architecture.

- Ragas, TruLens, or DeepEval.

- GitHub Copilot or AI-assisted development.

- Exposure to fine-tuning or model optimization.

Candidate Profile :

- Strong programming and problem-solving skills.

- Hands-on experience building production-oriented GenAI solutions.

- Ability to convert use cases into working AI applications.

- Good understanding of LLM, RAG, and agent concepts.

- Comfortable working in agile engineering teams.

- Strong debugging and troubleshooting capabilities.