Mandatory skill: Expertise in LangChain, LlamaIndex, Semantic Kernel, AutoGen, or equivalent
Key Responsibilities
- Agent Development: Build and orchestrate autonomous AI agents with multi-step reasoning, tool usage, and workflow chaining using frameworks like LangChain, CrewAI, AutoGen, Semantic Kernel, or LlamaIndex.
- LLM Integration & Optimization: Deploy, fine-tune, and serve open-source LLMs (e.g., Llama 3) using Databricks Model Serving; optimize latency, throughput, and cost.
- RAG & Knowledge Systems: Design advanced RAG pipelines leveraging vector search, embeddings, semantic ranking, and enterprise data sources (structured + unstructured).
- Context Engineering: Develop prompt strategies, memory frameworks, and metadata tagging to improve contextual accuracy and response quality.
- UI & Experience Design: Build intuitive AI-driven applications using Databricks Apps (Streamlit/Dash) or modern web frameworks to enable business consumption.
- Data Engineering for AI: Build reliable data pipelines (batch & streaming) supporting training, inference, and feature generation using Delta Lake.
- Security & Governance: Implement enterprise-grade controls using Unity Catalog (row/column-level security, lineage, auditability) aligned with compliance standards.
- LLM Guardrails & Responsible AI: Implement guardrails (e.g., NeMo Guardrails) for prompt injection prevention, hallucination mitigation, and safe output handling.
- MLOps & AIOps: Establish CI/CD pipelines for AI models and agents, including versioning, monitoring, drift detection, observability, and incident response.
- Performance & Cost Optimization: Optimize model performance, GPU/compute usage, and inference cost efficiency across environments.
- Testing & Evaluation
- Collaboration & Stakeholder Engagement
- Documentation & Knowledge Transfer
Required Skills and Qualifications
- Databricks & Lakehouse
- Strong experience with Unity Catalog, Delta Lake, Vector Search, Databricks Workflows, and Model Serving
- Hands-on with Lakehouse architecture patterns
- LLMs & Generative AI
- Experience with open-source LLMs (Llama, Mistral, etc.), prompting techniques, and fine-tuning approaches
- Strong knowledge of RAG architectures and embedding strategies
- AI Engineering & Frameworks
- Expertise in LangChain, LlamaIndex, Semantic Kernel, AutoGen, or equivalent
- Experience building agentic workflows and multi-agent systems
- Programming
- Advanced Python proficiency (APIs, web apps, orchestration, data processing)
- Familiarity with REST APIs and microservices architecture
- MLOps & Monitoring
- Experience with MLflow, CI/CD pipelines, model lifecycle management, and observability tools
- Knowledge of drift detection and model performance monitoring
- Data Engineering Foundations
- Experience with Spark, SQL, and large-scale data processing
- Familiarity with streaming frameworks (Kafka, Structured Streaming)
- Security & Governance
- Expertise in AI security risks (prompt injection, jailbreaks, data leakage)
- Experience implementing governance frameworks and compliance controls.