Gen AI Engineer

Roles and Responsibilities :

• Design, develop, and deploy large language models using Python and Generative AI techniques to solve complex business problems.
• Collaborate with cross-functional teams to integrate AI solutions into existing systems and applications.
• Develop and maintain high-quality codebase for scalable, efficient, and reliable AI models.
• Troubleshoot issues related to model performance, data quality, and system integration.

Job Requirements :

- 4–8 years of experience in Python development, AI/ML, and Generative AI. - Strong hands-on experience delivering GenAI/Agentic AI solutions in production environments. - Hands-on experience with LangChain, LangGraph, AI Agents, and workflow orchestration. Designing workflows involving planning, tool calling, memory, and autonomous task execution. - Strong understanding of: RAG, Embeddings, Vector Search, Vector databases specifically (FAISS, Chroma, Pinecone, Azure AI Search, etc.)., Prompt Engineering, LLM Optimization, Semantic Search - Practical experience with Microsoft Copilot, ChatGPT, Azure OpenAI/OpenAI, and open-source LLMs. - Strong Python programming, SQL, API development, and debugging skills. Following software engineering practices such as code reviews, testing, documentation, and version control. - Experience with Databricks, MLflow, Model Serving, Unity Catalog, and cloud-based AI workloads is preferred. - Experience implementing observability, tracing, monitoring, and troubleshooting for AI applications. - Experience with CI/CD, MLOps, AI governance, and production deployment best practices. - Monitoring hallucinations, retrieval quality, latency, and token consumption. Building evaluation and benchmarking frameworks.