Job Description:
Key Responsibilities
· Design and architect end-to-end GenAI solutions using LLMs (OpenAI, Azure OpenAI, Google Gemini, Anthropic Claude, etc.)
· Lead the implementation of prompt engineering, RAG (Retrieval-Augmented Generation), fine-tuning, and agentic AI systems
· Define AI architecture patterns, best practices, and governance frameworks
· Build scalable pipelines for data ingestion, vectorization (embeddings), and semantic search
· Collaborate with business stakeholders to identify AI use cases and translate them into technical solutions
· Implement and manage AI model deployment on cloud platforms (Azure, AWS, GCP)
· Ensure responsible AI practices, including security, compliance, and bias mitigation
· Integrate GenAI solutions with enterprise systems (APIs, microservices)
· Mentor engineering teams and drive AI adoption roadmap
· Monitor solution performance and continuously improve accuracy, latency, and cost efficiency Technical Skills
· Strong experience in Python and familiarity with ML/AI frameworks
· Knowledge of containerization (Docker, Kubernetes
· Experience with REST APIs, microservices architecture, and system design
· Familiarity with DevOps/MLOps practices (CI/CD, model monitoring, versioning)
· Hands-on experience with:
o LLM frameworks: LangChain, LlamaIndex, Semantic Kernel
o Vector databases: Pinecone, FAISS, Weaviate, Chroma
o Cloud AI services: Azure OpenAI, AWS Bedrock, Google Vertex AI
· Deep understanding of:
o Transformer architectures and NLP concepts
o Prompt engineering and evaluation techniques
o RAG pipelines and embeddings
Mandatory skills: Gen AI, Python, AWS, Amazon Q, Kiro, Java, Spring boot, Microservice