AI Engineer

    Build and integrate AI-driven capabilities into enterprise applications and workflows using leading LLM platforms.

•      Design and implement Retrieval-Augmented Generation (RAG) architectures to enable AI systems to securely leverage internal knowledge and data sources.

•      Develop and orchestrate AI agents capable of executing multi-step, decision-based business processes.

•      Own production AI systems end-to-end, including deployment, versioning, monitoring, scaling, and cost optimization.

•      Define, implement, and maintain evaluation metrics for AI quality, reliability, latency, and cost efficiency.

•      Collaborate closely with Leadership, Product and Engineering teams to identify, prioritize, and deliver high-impact AI solutions.

•      Ensure AI solutions follow enterprise standards for security, data privacy, reliability, and maintainability.

Must-Have (Non-Negotiable) Skills & Experience

•      7 to 8 years of overall software engineering experience, with 3 to 4 years of hands-on work on production AI / LLM systems.

•      Strong proficiency in Python, with experience writing production-quality, testable, and maintainable code.

•      Proven experience designing and implementing RAG pipelines, including document ingestion, embeddings, retrieval, and response generation.

•      Hands-on experience with vector databases (e.g., Qdrant, FAISS, ChromaDb, or similar).

•      Practical experience using LLM orchestration frameworks such as LangChain, LlamaIndex, Autogen, Haystack, or Semantic Kernel.

•      Prior experience building AI solutions in SaaS or enterprise-scale software environments.

•      Experience integrating with major LLM providers such as OpenAI, Anthropic Claude, or Google Gemini.

•      Solid understanding of prompt engineering, context engineering (context window management), and output control techniques.

•      Experience deploying AI systems to cloud environments (AWS, Azure, or GCP) using Docker and Kubernetes.

•      Working knowledge of LLMOps & MLOps practices, including model versioning, CI/CD, monitoring, and rollback strategies.

•      Experience in implementing guardrails in AI Solutions along with Observability.

Preferred / Nice-to-Have Qualifications

•      Exposure to multimodal AI systems, model fine-tuning, or reinforcement learning from human feedback (RLHF).

•      Familiarity with Model Context Protocol (MCP).

•      Understanding of AI cost optimization, latency tuning, and performance benchmarking in production.

•      Experience with domains such as eCommerce, Retail, HR, Finance, Legal, Compliance, etc

Language & Documentation Expectations

•      All production AI code must be clearly documented, version-controlled, and supported by appropriate tests.

•      AI pipelines, prompts, and agent workflows must include design documentation and usage guidelines.

•      Each production AI system must have defined ownership, monitoring dashboards, and operational runbooks.

•      Clear documentation of model limitations, assumptions, and fallback behaviours is mandatory.