SeniorLead Generative AI Engineer

Required Skills:

Responsibilities Design and build production-grade Generative AI applications such as AI assistants enterprise chatbots document intelligence systems knowledge copilots and AI-powered automation platforms. Develop and deploy LLM-powered applications using orchestration frameworks such as LangChain LangGraph LlamaIndex Strands AutoGen CrewAI Haystack DSPy and Semantic Kernel. Build advanced Retrieval Augmented Generation (RAG) systems including Graph RAG Hybrid RAG multi-hop retrieval Agentic RAG and knowledge graphbased retrieval pipelines. Develop AI agents and multi-agent systems capable of reasoning tool usage and task orchestration using frameworks such as LangGraph AutoGen CrewAI and Strands. Build Python backend services and scalable APIs using FastAPI and modern backend frameworks while following microservices architecture principles. Design scalable backend architectures for AI applications with asynchronous processing task queues and distributed workloads. Integrate foundation models and LLM providers such as OpenAI Anthropic Claude LLaMA and open-source LLMs Google Gemini and Hugging Face models. Implement document ingestion pipelines including chunking strategies embedding generation metadata enrichment indexing and semantic retrieval. Build semantic search and vector retrieval systems using vector databases such as Pinecone Weaviate Milvus FAISS ChromaDB Qdrant and OpenSearch vector search. Implement embedding pipelines using embedding models from OpenAI Hugging Face Sentence Transformers or similar providers. Develop AI pipelines for document processing summarization knowledge extraction and conversational interfaces. Deploy AI applications on AWS cloud services including Amazon Bedrock SageMaker EC2 Lambda ECS EKS S3 DynamoDB RDS OpenSearch API Gateway and CloudWatch. Build containerized applications using Docker and deploy them using Kubernetes ECS or EKS. Implement scalable AI inference infrastructure using modern model serving technologies such as vLLM Hugging Face TGI (Text Generation Inference) Triton Inference Server or Ray Serve. Build robust CI/CD pipelines and automate deployments for AI applications. Implement observability monitoring and evaluation for AI systems using tools such as LangSmith LangFuse TruLens Arize Ragas and DeepEval. Optimize AI systems for latency throughput cost efficiency and reliability in production environments. Integrate AI applications with enterprise systems APIs data platforms and external services. Mentor engineering teams and establish best practices for building scalable AI applications and backend systems. Required Experience At least 2 years of hands-on experience building Generative AI or LLM-based applications in production. min 5 years of experience designing and developing Python applications and backend systems. Strong experience developing REST APIs and microservices using FastAPI. Hands-on experience integrating backend applications with AWS cloud services. Experience building RAG pipelines AI agents and LLM orchestration workflows. Required Skills Strong programming expertise in Python. Experience with backend frameworks such as FastAPI Pydantic and asynchronous programming. Experience with Generative AI frameworks such as LangChain LangGraph LlamaIndex Strands AutoGen CrewAI Haystack DSPy or Semantic Kernel. Experience implementing advanced RAG architectures including Graph RAG and hybrid retrieval pipelines. Experience working with vector databases and semantic search systems. Familiarity with machine learning and AI libraries such as PyTorch TensorFlow Hugging Face Transformers Sentence Transformers NumPy Pandas and Scikit-learn. Experience deploying applications on AWS cloud infrastructure. Experience building containerized services using Docker and deploying using Kubernetes or container orchestration platforms. Strong understanding of scalable backend architecture distributed systems and cloud-native application development. Nice to Have Experience with model serving frameworks such as vLLM Triton Inference Server Ray Serve or Hugging Face TGI. Experience building Agentic AI workflows and autonomous AI systems. Familiarity with AI evaluation frameworks guardrails and LLM safety mechanisms. Experience building enterprise AI platforms or internal AI developer tooling.