AI Engineer

This is us

At Avenga, we believe that human creativity empowers technology that matters. Operating globally, our 6000+ specialists provide a full spectrum of services, including business and tech advisory, enterprise solutions, CX, UX and UI design, managed services, product development, and software development.

This is the job

This role focuses on the design and development of business agents using the SADK framework. You will work closely with senior engineers and domain experts to implement agent solutions, apply prompt engineering techniques, and translate business and clinical requirements into scalable and compliant configurations. The position is highly hands-on, with the majority of time spent on active development.

This is you

• 3–5 years of experience in software engineering
• 1–2+ years of hands-on experience with AI/ML and LLM-based applications
• Good understanding of prompt engineering and LLM application development
• Practical experience with OpenAI, Anthropic, or Azure OpenAI APIs
• Solid programming skills in Python and/or TypeScript
• Experience implementing or contributing to RAG (Retrieval-Augmented Generation) solutions
• Familiarity with vector databases and semantic search concepts
• Basic experience with agent frameworks (e.g., LangChain, AutoGen, or similar)
• Interest in evaluating and improving LLM-powered systems

This is your role

• Develop and enhance business agents using the SADK framework
• Implement agent components such as Knowledge, Review, Triage, Workflow, or Research agents
• Apply prompt engineering techniques suitable for clinical and regulated environments
• Build and maintain RAG pipelines with guidance from senior team members
• Contribute to optimizing agent performance in terms of accuracy, latency, and cost
• Participate in testing, evaluation, and validation of LLM-based agents
• Collaborate with analysts and engineers to translate requirements into technical solutions
• Actively contribute to development tasks, with a strong focus on coding