We are seeking a Senior AI Engineer to join our engineering team and lead the effort in modernizing our e-commerce platform with AI capabilities.
You will be responsible for the architecture, development, and integration of advanced AI systems, including Retrieval-Augmented Generation (RAG) pipelines, autonomous agents, and fine-tuned language models, within a mature, enterprise-grade .NET environment. Besides hands-on engineering, you will influence technical direction, mentor fellow engineers, and play a key role in shaping our long-term AI strategy.
Key Responsibilities
- Lead the design and implementation of production-grade RAG architectures that connect large language models to proprietary product, customer, and operational data.
- Architect and build AI agent systems that automate complex e-commerce workflows, including customer support, merchandising, and order management.
- Drive the strategy and execution of fine-tuning foundation models on domain-specific datasets to enhance relevance, accuracy, and business alignment.
- Evaluate, select, and integrate third-party AI services and APIs (e.g., OpenAI, Anthropic, Amazon Bedrock) into existing .NET applications and microservices.
- Define and promote best practices for prompt engineering, evaluation frameworks, model versioning, and responsible AI use across the engineering organization.
- Collaborate closely with backend, frontend, data engineering, and product teams to deliver end-to-end AI features within the current platform architecture.
- Own the performance, reliability, cost optimization, and observability of AI systems in production.
- Mentor mid-level and junior engineers, conduct code reviews, and raise the technical standard of the team.
- Proactively identify high-impact opportunities where AI can generate measurable business value.
What you will do:
- 7+ years of professional software engineering experience, including at least 3 years focused on machine learning or AI engineering.
- Extensive hands-on experience developing LLM-based applications, such as RAG, agent frameworks, and model fine-tuning in production environments.
- Strong proficiency in C# / .NET with proven experience managing enterprise-scale .NET codebases.
- Solid knowledge of Python for ML experimentation, training pipelines, and prototyping.
- Experience working with vector databases (e.g., Qdrant, Weaviate, Milvus, Amazon OpenSearch, Pinecone) in production.
- Proficiency with orchestration frameworks like Semantic Kernel, LangChain, or AutoGen.
- Strong understanding of RESTful APIs, microservices architecture, and distributed systems on AWS.
- Proven ability to make architectural decisions and communicate technical trade-offs to both engineering and non-technical stakeholders.
- Track record of leading complex technical initiatives from design to production deployment.
- Strong analytical skills and the ability to translate ambiguous business problems into clear, well-defined AI solutions.
Nice to have:
- Experience in the e-commerce domain (catalog, search, recommendations, personalization, customer service).
- Hands-on experience with MLOps practices, including model deployment, monitoring, A/B testing, and CI/CD for ML pipelines.
- Familiarity with AWS AI and ML services such as Amazon Bedrock, Amazon SageMaker, Amazon Comprehend, and Amazon Kendra.
- Practical experience working with AWS infrastructure services like Lambda, ECS, Step Functions, and S3 in AI workloads.
- Knowledge of embedding models, re-ranking strategies, and semantic search optimization at scale.
- Experience with platform modernization or large-scale migration projects in enterprise environments.
- Experience mentoring engineers or leading technical guilds and working groups.
- Contributions to open-source AI/ML projects or published research.