Agentic AI Engineer 2

Responsibilities:

• Design and develop autonomous AI agents using modern Agentic AI frameworks.
• Build and optimise Retrieval-Augmented Generation (RAG) pipelines for enterprise use cases.
• Develop LLM-powered applications using APIs from OpenAI, Anthropic, Google Gemini, Azure OpenAI, or open-source models.
• Implement prompt engineering strategies to improve response quality and reliability.
• Build multi-agent workflows for complex task orchestration.
• Integrate AI agents with enterprise systems, APIs, databases, and business workflows.
• Evaluate AI models using automated evaluation frameworks and establish quality benchmarks.
• Develop scalable backend services for AI applications using Python and FastAPI.
• Implement observability, monitoring, logging, and performance optimisation for AI systems.
• Work closely with product managers and engineering teams to translate business problems into AI-driven solutions.
• Stay updated with emerging advancements in LLMs, Agentic AI, and Generative AI technologies.

Requirements:

• 3.6-5 years of software development experience with strong expertise in Python.
• Hands-on experience with Agentic AI frameworks such as LangGraph, LangChain, CrewAI, AutoGen, or similar.
• Strong understanding of Large Language Models (LLMs) and Generative AI concepts.
• Experience building RAG applications using vector databases.
• Experience with vector databases such as Pinecone, Weaviate, ChromaDB, FAISS, or Milvus.
• Knowledge of embeddings, semantic search, chunking, and retrieval optimisation.
• Strong prompt engineering skills.
• Experience with FastAPI or similar backend frameworks.
• Good understanding of REST APIs and microservices architecture.
• Experience with Git and modern software development practices.
• Familiarity with Docker and containerised deployments.

Good-to-Have Skills:

• Experience with Model Context Protocol (MCP).
• Knowledge of AI evaluation frameworks such as DeepEval, Ragas, LangSmith, or Promptfoo.
• Experience with LlamaIndex.
• Familiarity with Hugging Face ecosystem and open-source LLMs.
• Experience with cloud platforms such as GCP, AWS, or Azure.
• Understanding of Kubernetes and CI/CD pipelines.
• Experience with monitoring tools such as Langfuse, Phoenix, or MLflow.
• Knowledge of AI safety, guardrails, and responsible AI practices.

Preferred Qualifications:

• Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Information Technology, or a related field.
• Strong problem-solving and analytical skills.
• Excellent communication and collaboration abilities.
• Passion for emerging AI technologies and continuous learning.