AI Engineer (LLMs | RAG | LangChain | Python)

AI Engineer (LLMs | RAG | LangChain | Python)

Location: Remote – India

Job Type: Full-time

Department: Engineering

Experience: 4+ years (Mandate)

About the Role

We are looking for a highly skilled AI Engineer to design, build, and deploy advanced AI systems powered by modern large language models and machine learning frameworks.

This role focuses on developing production-ready AI applications using LLMs, Retrieval-Augmented Generation (RAG), and agent-based architectures. You will work closely with engineering and product teams to integrate cutting-edge AI capabilities into real-world applications at scale.

Key Responsibilities

• Design, develop, and deploy machine learning and deep learning models for production environments.
• Build AI-powered applications using modern LLM ecosystems and reasoning frameworks.
• Implement RAG pipelines, agent-based systems, and context-aware AI workflows.
• Integrate models such as GPT-4o, Llama 3.1, Claude 3.5 Sonnet, and Google Gemini into scalable applications.
• Optimize model performance, latency, and scalability using advanced inference and acceleration tools.
• Collaborate with cross-functional teams across product, engineering, and data functions.
• Build and maintain AI infrastructure, tooling, and deployment pipelines.
• Stay updated with emerging AI technologies and continuously evaluate new frameworks.

Required Qualifications

• 4+ years of experience in AI/ML engineering or applied machine learning.
• Strong proficiency in Python and deep learning frameworks such as PyTorch.
• Hands-on experience building and deploying production AI systems.
• Experience working with LLM orchestration frameworks and modern AI tooling.
• Strong understanding of model lifecycle: data preparation, training, evaluation, deployment, and monitoring.
• Ability to work effectively in a remote, collaborative environment.

Required Technical Skills

Candidates should have practical experience with:

• Hugging Face ecosystem
• LangChain or similar LLM orchestration frameworks
• Retrieval-Augmented Generation (RAG)
• Agent-based or Mixture-of-Agents architectures
• OpenAI (GPT-4o / 4o mini)
• Google Gemini (1.5 Pro or similar)
• Llama 3.x models
• Anthropic Claude models
• Cohere or comparable LLM platforms
• Model deployment and inference optimization
• AI infrastructure and API integrations

Preferred / Nice to Have

• Experience with Groq, Fireworks AI, or accelerated inference platforms
• Multi-modal AI systems
• Production monitoring and evaluation pipelines
• Experience deploying scalable AI services on cloud platforms
• Advanced degree in Computer Science, AI, or related fields

Apply via LinkedIn or share your resume at:

📩 [email protected] - with links to your GitHub, portfolio or live production work demonstrating Next.js expertise.

(Please include a brief introduction, links to your GitHub, portfolio or examples of AI systems you have built or deployed., current role, notice period, current and expected CTC)