We are seeking an AI Engineer specializing in Generative AI and Agentic AI systems.
This role focuses on designing, developing, and operationalizing intelligent AI agents, Large Language Model (LLM)-based applications, Retrieval-Augmented Generation (RAG) systems, and autonomous multi-agent workflows.
Key Responsibilities
1. GenAI Development & LLM Engineering
• Build and deploy LLM-based applications leveraging frameworks like LangChain.
• Develop RAG pipelines using vector databases for enterprise knowledge retrieval.
• Develop data pipelines to create structured and unstructured datasets for LLM and agent workflows.
• Optimize prompts, system instructions, and memory architectures for robust, domain-specific reasoning.
• Evaluate model performance-accuracy, hallucination mitigation, latency, and safety compliance.
2. Agentic AI Design & Autonomous Workflow Engineering
• Implement agentic systems capable of planning, reasoning, tool usage, and multi-step decision-making.
• Build multi-agent ecosystems (task agents, planning agents, critic agents, evaluation agents) to automate complex workflows.
• Integrate agents with APIs, enterprise systems, and external tools to create end-to-end autonomous solutions.
• Ensure agent alignment with Responsible AI principles-traceability, guardrails, human oversight.
3. AI Systems Integration & Deployment
• Build scalable microservices and APIs for GenAI and agentic components.
• Deploy models and agents using Azure ML or Kubernetes-based stacks.
4. Collaboration & Influence
• Engage with business and product stakeholders to convert ambiguous use cases into technical solutions.
• Support internal capability building-AI best practices, prompt engineering, GenAI safety, and evaluation frameworks.
Required Skills & Qualifications
• Strong hands-on expertise in Python, LLM frameworks, and ML/DL libraries (Transformers, PyTorch, TensorFlow, scikit-learn).
• Experience with API development, microservices, Docker, and Kubernetes.
• Experience building RAG systems with vector databases and embeddings.
• Experience with agentic frameworks or building custom autonomous agents.
• Strong understanding of LLM safety, hallucination mitigation, and evaluation techniques.
• Cloud proficiency in Azure (or any other hyperscalers - AWS, GCP etc.)
Soft Skills
• Strong analytical reasoning, problem-solving, and design thinking skills.
• Comfortable working in fast-paced, agile, innovation-driven environments.
• Curiosity and a passion for emerging AI research, prototyping, and experimentation.