GenAI Solution Designer & Developer

Design and build LLM-powered applications using RAG, embeddings, and vector search architectures. Develop Copilot-based AI assistants and agents for enterprise use cases (automation, Q&A, workflow orchestration). Engineer end-to-end GenAI pipelines including prompt engineering, context handling, and response orchestration. Build reusable AI components (agents, pipelines, guardrails) to accelerate solution delivery.

Copilot & AI Agent Development Develop and customize copilots using Microsoft Copilot Studio / Azure Foundry. Integrate copilots with enterprise systems (ERP, CRM, ServiceNow, APIs). Design conversational workflows, triggers, and automation actions. Enable enterprise-grade features such as: Role-based access and identity integration. Knowledge grounding using enterprise data. Responsible AI guardrails (toxicity, hallucination control).

Snowflake Cortex / Data AI Engineering Develop AI-powered applications using Snowflake Cortex AI functions and Snowpark. Implement vector search, semantic models, and AI-driven analytics workflows. Integrate structured and unstructured data pipelines to support AI models. Build self-service AI capabilities on data platforms with governance and cost optimization.

AI/ML Engineering & MLOps Build and deploy models using Azure OpenAI, AWS Bedrock, or similar platforms. Create scalable pipelines for: Model deployment. Monitoring and observability. Continuous improvement loops.

GOOD TO HAVE

Implement AI guardrails, evaluation frameworks, and feedback loops for production systems. SDLC Automation with GenAI Leverage tools like GitHub Copilot for: Code generation, test automation, debugging, and documentation. Automate SDLC activities using GenAI (requirements code testing deployment). Enable developer productivity improvements and automation-first engineering. GenAI/LLM solutions (RAG, vector databases, prompt orchestration). Align business priorities with AI outcomes with tangible outcomes and optimizations. Define and curate strategy for model training, inference, and monitoring, AIOps, AI governance elements, Responsible AI, fairness, and explainability. Integrate GenAI into enterprise workflows (chatbots, copilots, knowledge assistants) as applicable and adoptable for relevant business operations architecting solutions across Azure and AWS. Manage AIOps and related governance from data collection to retraining and monitoring model drifts.

Hands-on knowledge of data models, SQL, and data lifecycle management. Strong knowledge of AI/ML algorithms, data structures, and performance optimization. Proficiency in programming languages such as Python, SQL, and PySpark. Experience with cloud platforms (AWS, Azure) and big data technologies (Spark, Snowflake).

Other Requirements

Candidate must have: Must be on W2. Valid visa with a minimum of 12 months validity. Resume should have a LinkedIn URL to validate. Must be comfortable with 5 days onsite working as per customer expectation along with a 6-month contract-to-hire.