GenAI / Agentic AI Engineer (4–6 Years Experience)

Key Skills & Responsibilities:

• Strong expertise in Prompt Engineering for LLMs and SLMs.

• Hands-on experience with SLMs and CrewAI for building and orchestrating multi-agent workflows.

• Proficiency with Agentic AI frameworks (LangChain, LangGraph, etc.) and Generative AI solutions.

• Experience in DevOps / LLMOps / MLOps, covering deployment, monitoring, observability, and CI/CD for AI systems.

• Skilled in scalability and orchestration using Docker, Kubernetes, and Cloud / On-Prem environments.

• Good understanding of the Azure , AWS AI/ML stack for enterprise-grade deployments.

• Strong foundation in System Design & Architecture for distributed AI solutions.

• Solid programming background with conceptual programming and best engineering practices.

Your Contribution:

Roles & Responsibilities: GenAI / Agentic AI Engineer

1. GenAI / Agentic AI Development

• Design, develop, and deploy agentic AI workflows using frameworks like CrewAI, LangChain, LangGraph, and custom orchestration layers.

• Build and fine-tune SLMs and LLMs for task-specific use cases (retrieval, summarization, reasoning, decision support).

• Implement prompt engineering & prompt chaining strategies for reliability and scalability.

2. System Architecture & Design

• Contribute to AI solution architecture ensuring modular, scalable, and cloud-native designs.

• Integrate AI components with enterprise systems, APIs, and external data sources.

• Develop RAG pipelines, vector database integrations (Pinecone, Weaviate, FAISS), and multi-agent systems.

3. MLOps / LLMOps / DevOps

• Own end-to-end lifecycle management: model training, testing, deployment, monitoring, and upgrades.

• Implement observability & telemetry (latency, bias, drift detection, performance monitoring).

• Ensure CI/CD pipelines for AI models and services with Docker, Kubernetes, and GitOps practices.

4. Cloud & Infrastructure

• Deploy AI workloads on Azure AI/ML stack (Azure OpenAI, Cognitive Services, Azure ML).

• Optimize AI solutions across cloud and on-prem environments for cost, performance, and security.

• Ensure high availability and scalability of AI services.

5. Governance & Risk Management

• Implement guardrails, safety checks, and compliance frameworks for responsible AI.

• Conduct bias testing, red-teaming, and stress testing for models and agents.

• Document AI system behavior, data lineage, and model decisions for audit readiness.

6. Collaboration & Knowledge Sharing

• Work closely with data scientists, solution architects, and business stakeholders to translate requirements into agentic AI solutions.

• Provide technical mentorship on SLMs, agent orchestration, and AI system design.

  • Support POCs, client demos, and technical workshops showcasing AI capabilities.