- Strong hands-on experience in Python 2) Good experience with Generative AI / Large Language Models (LLMs) 3) Solid understanding of NLP, embeddings, transformers, prompt engineering, and LLM application design 4) Experience building RAG pipelines 5) Hands-on experience with orchestration frameworks such as - LangChain / LlamaIndex / Semantic Kernel / AutoGen / CrewAI / LangGraph 6) Experience with vector databases such as - FAISS, Pinecone, Chroma, Weaviate, Milvus, Elasticsearch/OpenSearch 7) Exposure to REST APIs / FastAPI / Flask for serving AI applications 8) Strong understanding of ML lifecycle, deployment, testing, and performance tuning
- Design and develop Generative AI / LLM-based applications for enterprise use cases such as chatbots, summarization, document intelligence, search, Q&A, code assistants, and workflow automation. 2) Build and optimize RAG (Retrieval-Augmented Generation) pipelines using embeddings, vector databases, chunking, retrieval strategies, and prompt orchestration. 3) Work with foundation models / LLMs from providers such as OpenAI, Anthropic, Cohere, Hugging Face, AWS Bedrock, or open-source models. 4) Develop robust backend services and APIs to integrate GenAI solutions into enterprise platforms and applications. 5) Fine-tune, evaluate, and improve model responses through prompt engineering, guardrails, grounding, and performance optimization. 6) Build scalable AI pipelines on AWS or Databricks for training, experimentation, deployment, and monitoring. 7) Collaborate with Data Science, ML Engineering, Application Engineering, and Product teams to productionize GenAI use cases. 8) Ensure best practices in model deployment, observability, security, governance, and responsible AI. 9) Contribute to architecture discussions, PoCs, reusable frameworks, and accelerators for GenAI adoption.
Cloud / Platform Skills Candidate should have hands-on experience in either AWS or Databricks: AWS - AWS Bedrock, SageMaker, Lambda, ECS/EKS, S3, API Gateway, CloudWatch, IAM Experience deploying scalable AI/ML workloads on AWS OR Databricks - Databricks notebooks, MLflow, Model Serving, Delta Lake, Unity Catalog Experience building and deploying AI/ML / GenAI use cases on Databricks platform Exposure to MLOps / LLMOps concepts Knowledge of model monitoring, evaluation, experimentation, and versioning Experience with Docker, Kubernetes, CI/CD pipelines Familiarity with guardrails, AI safety, content filtering, and governance Exposure to multimodal AI, agentic workflows, or autonomous AI systems Understanding of structured/unstructured data processing pipelines
