Role Summary

Experienced Generative AI (GenAI) Engineer with 7–10 years of software/ML engineering experience and a strong track record of delivering LLM-powered applications into production. The role involves designing and building GenAI solutions such as RAG-based assistants, copilots, agent workflows, and enterprise knowledge systems, ensuring they are secure, scalable, observable, and cost-efficient. The engineer will work closely with product, data, security, and platform teams to create measurable business outcomes while establishing best practices for LLMOps, evaluation, and responsible AI.

Key Responsibilities

• Build and productionize LLM-powered applications (chatbots, copilots, summarization, search/Q&A, document intelligence) with measurable quality and reliability.
• Design and implement Retrieval-Augmented Generation (RAG) solutions: chunking strategies, embeddings, hybrid search, ranking, prompt templates, grounding, and citation-based responses.
• Develop agentic workflows: tool/function calling, multi-step reasoning pipelines, orchestration, retry/fallback logic, and state management for complex tasks.
• Implement LLMOps practices: prompt/version control, evaluation pipelines, model routing, A/B testing, cost monitoring, and automated regression testing.
• Create scalable inference services and APIs (REST/gRPC) with performance optimization (latency, throughput, caching, streaming responses).
• Build and maintain vector and knowledge layers: indexing pipelines, metadata enrichment, access control filtering, freshness strategies, and re-index automation.
• Implement guardrails and safety controls: input/output filtering, jailbreak detection patterns, PII redaction, policy-based access, content moderation, and audit logging.
• Establish observability and monitoring: quality metrics, grounding metrics, hallucination rate, drift, token usage, latency, error rates, and user feedback loops.
• Collaborate with security/compliance to ensure enterprise requirements (RBAC, encryption, data residency, retention, DLP) are built into the solution.
• Mentor junior engineers and contribute reusable components, internal libraries, templates, and reference architectures.

Required Qualifications

• 7–10 years of experience in software engineering, ML engineering, or applied AI with multiple production deployments.
• Strong proficiency in Python with solid software engineering practices (testing, packaging, code reviews, design patterns).
• Hands-on experience building GenAI solutions using LLMs (OpenAI/Azure OpenAI/Anthropic or open-source), including prompt engineering and structured outputs.
• Experience with RAG systems and vector search concepts (embeddings, chunking, retrieval strategies, re-ranking, hybrid search).
• Experience building backend services using FastAPI/Flask (or equivalent), with secure API design and performance tuning.
• Strong understanding of LLM evaluation and quality measurement (golden datasets, automated scoring, human-in-the-loop feedback).
• Experience with containerization and deployment: Docker, Kubernetes (or managed alternatives), CI/CD pipelines.
• Strong fundamentals in data engineering concepts: ETL/ELT, data quality, schema evolution, metadata, logging, and lineage.
• Working knowledge of cloud services (Azure/GCP) and enterprise identity/security (IAM/RBAC, secrets management, network security).