Venon Solutions is a global leader in the design and manufacture industry, and they are seeking an AI Engineer to work across the full lifecycle of AI product development. The role involves shaping AI engineering best practices, contributing to infrastructure decisions, and developing scalable production systems.
Responsibilities:
- Build and deploy AI-driven systems and applications using OpenAI, Amazon Bedrock, Langchain, and LangGraph
- Prototype, fine-tune, and productionize LLM-based and retrieval-augmented generation (RAG) solutions; develop input/output guardrails to ensure model safety, reliability, and alignment with business goals
- Design and maintain robust evaluation pipelines to monitor model performance, correctness, and drift over time
- Work closely with cross-functional partners in Product, Research, and Engineering to align technical work with business needs
- Communicate technical concepts clearly to non-technical stakeholders and executive leadership
Requirements:
- Advanced English for fluent communication (B2 or Higher)
- 5+ years of experience as an AI Engineer
- Strong Python development skills, particularly around APIs, backend services, and AI/ML libraries
- Familiarity with Vertex AI to build a production-grade ML pipeline with model retraining and monitoring, among other tasks
- Experience building applications powered by OpenAI models and/or Bedrock foundation models, using frameworks like Langchain and LangGraph
- Ability to work autonomously to take projects from concept to production
- Excellent communication skills with the ability to explain technical details to diverse audiences
- Prior experience integrating AI/ML into production-grade systems at scale
- Exposure to Retrieval-Augmented Generation (RAG) pipelines and prompt engineering
- Experience contributing to architectural decisions for AI-driven platforms