Senior Specialist_Python/AI Engineer
merckgroup
Job Description
- Design, develop, and deploy AI/ML solutions using Python and state-of-the-art NLP technologies.
- Architect and implement Retrieval-Augmented Generation (RAG) systems for intelligent information retrieval and generation.
- Build and manage vector databases (Qdrant, Pinecone, Weaviate, etc.) with scalable indexing, optimization, and deployment strategies.
- Implement document preprocessing, chunking strategies, and metadata management for RAG pipelines.
- Leverage AWS AI/ML services (SageMaker, Bedrock, Kendra, Lambda, etc.) to build intelligent applications.
- Develop robust backend services and APIs using best practices in Python.
- Design secure and scalable cloud-based architectures on AWS.
- Integrate NLP APIs (OpenAI, Hugging Face, spaCy, etc.) for text analytics and understanding.
- Build user interfaces and dashboards using React and Streamlit.
- Collaborate with cross-functional teams to translate business requirements into technical deliverables.
- Mentor junior engineers and ensure adherence to coding and documentation standards.
- Experience with RAG frameworks such as LangChain, LlamaIndex, or Haystack.
- Knowledge of additional AWS AI services (Textract, Comprehend, Translate, OpenSearch, Kendra).
- Familiarity with MLOps practices, CI/CD pipelines (AWS CodePipeline, CodeBuild), and containerization (Docker, Kubernetes).
- Experience with data processing libraries (Pandas, NumPy) and ML frameworks (TensorFlow, PyTorch, scikit-learn).
- Strong understanding of vector database optimization, scaling, and hybrid search techniques.
- Knowledge of graph databases (Neo4j, Amazon Neptune) and knowledge graph integration with RAG systems.
- Experience with cost optimization, A/B testing, and observability tools (CloudWatch, X-Ray, Prometheus).
- Understanding of AWS security best practices, including IAM, KMS, and VPC design.
- Hands-on experience designing and implementing RAG architectures.
- Proficiency with backend databases (PostgreSQL, MySQL, MongoDB, DynamoDB, etc.), including schema design and optimization.
- Experience developing cloud-based solutions using AWS (SageMaker, Bedrock, Lambda, ECS/EKS, Step Functions).
- Practical experience with at least one vector database (Qdrant, Pinecone, Weaviate, Chroma, FAISS, Milvus, or pgvector).
- Hands-on experience integrating Large Language Models (GPT, Claude, Llama, or Titan) within RAG systems.
- Proficiency in working with embedding models (OpenAI, Cohere, Sentence Transformers, or Amazon Titan).