Job Summary
Role Summary
The AI Engineer will design, build, deploy, and operate production-grade Large Language Model (LLM) solutions. This role focuses on engineering rigor—turning LLM capabilities into reliable, scalable, and secure enterprise applications, and continuously improving them based on performance, cost, and user feedback.
Key Responsibilities
• Design and build LLM-powered applications using proprietary and open-source models.
• Implement prompt engineering, Retrieval-Augmented Generation (RAG), tool/function calling, and agent workflows.
• Deploy LLM solutions into cloud and enterprise environments with scalability and reliability.
• Build inference APIs, microservices, and CI/CD pipelines for AI applications.
• Monitor model quality, latency, cost, drift, and hallucinations in production.
• Fine-tune and enhance models using parameter-efficient techniques where required.
• Optimize inference performance using caching, batching, quantization, and prompt optimization.
• Ensure security, privacy, and responsible AI guardrails in all deployments.
• Collaborate with product, platform, and engineering teams to deliver enterprise AI solutions.
Required Skills & Experience
• Strong programming skills in Python; experience with backend APIs.
• Hands-on experience with LLM frameworks (LangChain, LlamaIndex, or equivalent).
• Experience building RAG pipelines using vector databases.
• Knowledge of Docker, Kubernetes, cloud platforms, and CI/CD pipelines.
• Familiarity with LLMOps / MLOps tools and monitoring systems.
Experience Level
• 11–15 years of overall software or ML engineering experience.
• 1–3+ years of hands-on experience delivering LLM or Generative AI solutions in production.
Success Expectations
• Production-grade LLM solutions running reliably at scale.
• Continuous improvement in quality, cost-effectiveness, and user outcomes.
• Reusable AI engineering patterns that accelerate enterprise AI adoption.
Key Responsibilities
2. To support as an Subject Matter Expert
3. To ensure knowledge up-gradation and work with new technologies so that the solution is current and meets quality standards and the client requirements
4. Ensuring a sufficient pool of skilled professionals in the designated technology, through activities such as conducting interviews, providing training sessions and offering mentorship.
5. To gather specifications and deliver solutions to the client organization based on understanding of a domain or technology.
6. To support competency development with envisioning and articulating propositions â building collaterals/ whitepaper creation, market trend analysis etc.
7. To recommend client value creation initiatives and implement industry best practices (on specific technology/product)