Agentic Ai

rsystems

Noida 4 Years Exp Posted 227d ago

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:

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.