GenAI Engineer at Impact

What You'll Do:

• Build and deploy agentic AI solutions that enable autonomous task completion across business functions
• Develop reusable AI libraries and SDKs that accelerate product discovery and empower engineering teams
• Build specialized AI tools that transform manual workflows into efficient automated processes
• Design and implement smart internationalization libraries that enhance global user experiences
• Create and optimize RAG systems that make company knowledge instantly accessible
• Develop scalable orchestration frameworks for AI agents to handle complex business processes
• Engineer prompt management systems and versioning tools for consistent AI interactions
• Build and maintain AI-powered knowledge graphs to improve information discovery and utilisation
• Create comprehensive LLM evaluation frameworks to ensure quality, accuracy, and performance
• Research, evaluate, and integrate third-party AI tools and SaaS solutions into the business
• Develop AI-powered analytics pipelines that transform unstructured data into actionable insights
• Implement conversational AI interfaces that streamline internal support and enhance productivity
• Stay current with advancements in GenAI, vector databases, and embeddings technologies
• Contribute to our internal AI community through knowledge sharing and best practices
• Work with cloud AI services to ensure scalability, reliability, and cost-effectiveness

What You Have:

• Software engineering fundamentals
• At least one year experience with Python and relevant AI/ML frameworks and libraries
• Basic understanding of cloud platforms (GCP preferred, AWS/Azure acceptable)
• Experience working with at least one AI provider API (OpenAI, Anthropic, or Google Gemini)
• Hands-on knowledge of LLM orchestration frameworks like LangChain and LangGraph
• Basic familiarity with LLM orchestration frameworks like LangChain or LangGraph
• Basic understanding of AI agents and automation concepts
• Understanding of vector databases and embedding models for semantic search
• Basic experience with pre-trained models and model deployment concepts
• Knowledge of RAG architectures and implementation patterns
• Ability to implement prompt engineering best practices for LLM applications
• Exposure to knowledge base and data indexing concepts (LlamaIndex familiarity is a plus)
• Strong problem-solving skills and attention to detail
• Excellent communication skills and ability to explain complex concepts to non-technical stakeholders
• Demonstrated hunger to learn, innovate, and stay current with the rapidly evolving AI landscape
• Ability to work collaboratively in a fast-paced environment