Location: Remote

Mode of work: Shift 3PM -12AM

Experience: 2 -4Yyears

Key Responsibilities

- Solution Architecture & Deployment

· Design and deploy scalable, secure GenAI architectures integrated into customer-facing products.

· Build REST APIs for AI/ML models and deploy them in containerized environments (Docker, Kubernetes) on cloud platforms (AWS, Azure, GCP).

- GenAI & LLM Development

· Fine-tune and optimize generative models including GPT, VAEs, GANs, and transformer-based architectures.

· Apply techniques like Retrieval-Augmented Generation (RAG) and prompt engineering to enhance model performance and relevance.

· Work with both commercial and open-source LLMs (e.g., GPT-4, Claude, LLaMA 3.2, Phi).

- Agentic AI Integration

· Primary Focus: Build, deploy, and optimize AI agents leveraging frameworks such as LangChain, LangGraph, CrewAI, AgentFlow, and Autogen.

· Implement orchestration strategies, multi-agent collaboration, tool integration, and memory/state management.

· Drive experimentation to create autonomous or semi-autonomous agents that solve real business workflows and decision-making processes.

- MLOps & Performance Optimization

· Establish MLOps pipelines covering model lifecycle: training, CI/CD, monitoring, and retraining.

· Use tools like Git, Docker, Kubernetes, and vector DBs to ensure productive and reliable deployment.

· Optimize resource utilization and infrastructure costs.

- Cross-Functional Collaboration

· Partner with engineering, data science,



and product teams to align technical solutions with business goals.

· Effectively communicate complex concepts across diverse technical and non-technical audiences.

· Stay current with industry advancements and drive innovation in GenAI and AI agent strategy.

Skills & Qualifications

Required

· Strong proficiency in Python, SQL, and GenAI frameworks (e.g., LangChain).

· Hands-on experience in building and deploying AI agents with orchestration, tool use, and state management.

· In-depth knowledge of LLM architecture, RAGs, embeddings, prompt tuning, and vector databases, agentic AI patterns (ReAct, tool-calling agents, multi-step reasoning, guardrails)

· Experience with cloud platforms (AWS, Azure, GCP) and containerization.

· Strong analytical, problem-solving, and communication skills.

· Data integration experience — REST APIs, Google APIs, SQL databases. Comfortable moving data between systems.

· Experience in Web development: FastAPIs, Typescript, async patterns, building production APIs, React, node.js, Component architecture, hooks, state management, consuming streaming APIs (SSE/WebSocket)

Preferred

· 2 years of hands-on experience with LLMs and GenAI in production settings.

· Exposure to agentic AI tools and multi-agent workflows (e.g., CrewAI, LangGraph, Autogen).

· Familiarity with MLOps and AI deployment best practices.

· Experience in client-facing or cross-functional AI initiatives.

· Publications, open-source contributions, or demonstrable projects showcasing AI agent development.

📌 Ai Engineer (India)
🏢 Wroots Global Private
📍 India