Artificial Intelligence Engineer

Job Overview:

We are seeking a deeply hands-on Senior Generative AI Engineer with 4-5 years of overall experience to design, develop, and deploy production-grade GenAI solutions. In this role, you will own technical workstreams end-to-end, taking complex AI systems from experimental POC phase through to highly scalable, reliable, and secure production deployment. The ideal candidate views LLMs as integrated components within larger microservice ecosystems and prioritizes application observability, reliability, and cost-efficiency.

Key Responsibilities:

• LLM & RAG Optimization: Design and architect scalable LLM-powered applications, chatbots, and enterprise solutions alongside highly optimized RAG pipelines using advanced semantic and hybrid search logic.
• Model & Workflow Integration: Build unified interfaces across major enterprise model platforms (OpenAI, Azure OpenAI, Amazon Bedrock, Google Vertex AI) and design complex prompt strategies and structured output configurations.
• Backend Application Development: Develop high-performing microservices, scalable AI processing layers, and backend systems utilizing Python and FastAPI.
• Productionization & Infrastructure: Containerize and deploy applications across major cloud platforms (AWS, Azure, or GCP) utilizing Docker, robust Git strategies, and automated CI/CD deployment logic.
• Evaluation & Observability: Implement strict GenAI validation, live response quality auditing, and contextual data-grounding steps to actively eliminate model hallucinations.

Required Skills & Qualifications:

• 4-5 years of overall experience in Software Engineering, AI/ML, or Data Science, featuring at least 2+ years of direct hands-on experience shipping Generative AI products.
• Comprehensive expertise utilizing core orchestration frameworks (LangChain, LlamaIndex, or Semantic Kernel) along with production vector databases and specialized text embeddings.
• Strong backend development background with expert-level command over Python, REST APIs, and Docker architectures.
• Preferred Experience: Prior exposure utilizing advanced evaluation toolsets (LangSmith, RAGAS, TruLens), enterprise data environments (Databricks, Snowflake), open-source model fine-tuning routines, or custom AI safety guardrails.