Role Overview
LLM Axis is looking for an Agentic AI Engineer to design, develop and implement intelligent AI agents, multi-agent systems and LLM-powered applications.
The candidate should have strong Python and software engineering fundamentals, along with hands-on experience building AI applications that can reason, interact with external systems, use tools and execute multi-step workflows.
The role involves developing practical AI applications for real-world use cases, supporting enterprise implementations and collaborating with technical and learning teams to create industry-relevant projects.
Key Responsibilities
AI Engineering & Development
- Design and develop AI agents and multi-agent workflows.
- Build LLM-powered applications using modern AI frameworks.
- Implement tool calling, planning, reasoning and task orchestration.
- Develop Retrieval-Augmented Generation (RAG) systems.
- Integrate LLM applications with APIs, databases and external services.
- Build agent memory, context management and workflow automation.
- Develop backend services and APIs for AI applications.
- Test, evaluate and improve agent performance and reliability.
- Implement logging, monitoring, guardrails and error handling.
- Optimise latency, token consumption and infrastructure costs.
- Collaborate with engineering teams to deploy production-ready AI solutions.
Enterprise Implementation
- Develop AI solutions for practical business use cases.
- Support integration of AI applications with existing enterprise systems.
- Troubleshoot application, model and integration issues.
- Participate in technical discussions, demonstrations and implementation reviews.
Knowledge Sharing & Technical Collaboration
- Document technical architectures and implementation approaches.
- Conduct internal technical knowledge-sharing sessions.
- Support the creation of practical technical demonstrations and project exercises.
- Collaborate with trainers and subject matter experts on industry-relevant learning projects.
Required Technical Skills
- Strong programming skills in Python.
- Practical experience with Generative AI and LLM applications.
- Experience with LangChain, LangGraph or similar frameworks.
- Understanding of RAG architecture, embeddings and vector databases.
- Familiarity with Pinecone, Chroma, Weaviate or FAISS.
- Understanding of REST APIs, backend development and databases.
- Knowledge of prompt engineering and structured outputs.
- Understanding of function calling, tool integration and multi-step workflows.
- Familiarity with Git, Docker and software development practices.
Preferred Skills
- Experience with AutoGen, CrewAI or LlamaIndex.
- Exposure to AWS, Azure or Google Cloud.
- Knowledge of Kubernetes, CI/CD and deployment practices.
- Experience with LLM evaluation and performance optimisation.
- Familiarity with fine-tuning and open-source language models.
- Experience deploying AI applications in production environments.
- Understanding of monitoring, security and application scalability.
Experience & Qualifications
- 2–5 years of overall experience in software engineering, Python development, AI/ML or backend engineering.
- At least 1–2 years of hands-on experience building LLM-powered or Generative AI applications.
- Practical exposure to RAG, AI agents, tool calling and API integrations.
- Experience developing and deploying working applications is preferred.
- Candidates should be able to demonstrate practical projects and explain their technical architecture.
Ideal Candidate
A hands-on AI engineer who can move beyond basic prompt-based demonstrations and build reliable, integrated AI agents and applications that solve real-world problems.