Generative AI Engineer

Invonto is a technology company focused on digital transformation, AI, product innovation, and custom software development. We work with organizations to build and improve real-world digital products, from business applications to cloud-based platforms., You’ll work on real-world projects involving large language models, AI-powered applications, intelligent automation, and enterprise integrations. This role is well suited for an engineer who enjoys both exploring new AI technologies and building reliable software around them.

What You’ll Do

• Design and develop AI-powered applications and solutions using generative AI and large language models
• Build custom AI solutions using self-hosted LLM as well as frontier models
• Develop AI capabilities including conversational assistants, intelligent search, document processing, summarization, content generation, and workflow automation
• Design and implement RAG solutions, embeddings, vector search, and AI-powered knowledge systems
• Develop and integrate AI agents and agentic workflows where appropriate
• Integrate AI capabilities with enterprise applications, APIs, databases, and business systems
• Design and evaluate prompts, model configurations, AI workflows, and responses
• Evaluate AI applications for accuracy, reliability, performance, and cost
• Develop prototypes and proof-of-concepts and help move successful solutions into production
• Work with structured and unstructured data to support AI applications
• Collaborate with developers, designers, project managers, and business stakeholders to translate business needs into practical AI solutions
• Contribute to technical architecture and implementation decisions
• Stay current with rapidly evolving AI models, tools, frameworks, and development practices
• Apply responsible AI practices with attention to data privacy, security, accuracy, and appropriate human oversight

• 3+ years of professional software development, AI engineering, or related experience
• Hands-on experience building applications using Generative AI and large language models
• Strong programming experience with Python and/or JavaScript/TypeScript
• Strong understanding of LLMs, prompt engineering, embeddings, vector databases, and RAG
• Experience building REST APIs
• Experience working with databases and structured and unstructured data
• Experience integrating AI capabilities into applications or business workflows
• Understanding of software development lifecycle and engineering best practices
• Ability to evaluate AI-generated results and troubleshoot issues involving accuracy, reliability, latency, and cost
• Strong problem-solving and analytical skills
• Ability to communicate effectively with both technical and non-technical team members
• Ability to work independently as well as collaboratively
• Curiosity and willingness to continuously learn as AI technologies evolve *