AI Engineer - Generative AI &Agentic Systems
Summary
Builds agentic AI and LLM-powered applications — including RAG, multi-agent workflows, and an AI Product Advisor for customers' digital sales journeys — using Python, FastAPI, LangChain/LangGraph/LangFuse, and Azure. Also owns prompt engineering, retrieval optimization, AI evaluation (DeepEval/G-Eval), observability, and production deployment via Docker, Kubernetes, and CI/CD.
Responsibilities:
- Design, develop, and implement agentic AI workflows and intelligent customer advisory capabilities to support customers throughout the end-to-end digital sales journey.
- Build and optimize LLM-powered applications, including Retrieval-Augmented Generation (RAG) solutions and multi-agent architectures.
- Develop scalable AI solutions using LangChain, LangGraph, and LangFuse.Translate complex business requirements and decision rules into reliable, scalable, and maintainable AI agent behavior.
- Design and implement prompt engineering, tool/function calling, context management, memory, and structured output strategies.
- Develop and integrate production-grade REST APIs using Python and FastAPI.Design and optimize retrieval solutions, including embeddings, vector search, ranking, retrieval optimization, and hybrid search.
- Establish quality assurance and automated evaluation approaches for AI-driven customer interactions using tools and frameworks such as DeepEval and G-Eval.
- Implement AI observability and monitoring to continuously assess application quality, reliability, and performance.
- Contribute to the deployment, operationalization, and production readiness of Generative AI solutions, including CI/CD and cloud-native environments.
- Apply software engineering best practices, including clean code, design patterns, automated testing, and maintainable architecture.
- Collaborate closely with business stakeholders, Product Owners, developers, and other technical teams throughout design, development, testing, and production rollout.
- Contribute to a cross-functional product team delivering an AI-powered Product Advisor that provides customers with personalized product recommendations and supports them from product discovery and consultation through contract completion.
Requirements:
- Strong professional experience in Python development.
- Hands-on experience designing and developing production-grade REST APIs with FastAPI.
- Solid understanding of software engineering principles, including clean code, design patterns, automated testing, and scalable application architecture.P
- roven practical experience developing and deploying Generative AI and LLM-powered applications.
- Strong knowledge and hands-on experience with:
- Prompt Engineering
- Function Calling / Tool Calling
- Agentic AI systems
- Multi-Agent architectures
- Context Management
- Memory Systems
- Structured Outputs
- Strong understanding of embeddings, vector databases, ranking, retrieval optimization, and hybrid search.
- Experience with Azure AI Search or comparable search technologies.
- Practical experience with relevant GenAI frameworks and tools, particularly:
- LangChain
- LangGraph
- LangFuse
- DeepEval / G-Eval
- OpenAI APIs
- AI observability and monitoring solutions
- PgVector or other vector databases
- Redis
- Docker
- Kubernetes
- CI/CD pipelines
- Ability to translate complex business requirements into robust technical solutions.
- Strong communication and collaboration skills with the ability to work effectively in cross-functional product teams.
Skills
As published by lever
Resume/CV, Full name, Email, Phone, Current location, Current company, LinkedIn URL