Source description
About the role
Key Responsibilities Solution Architecture & Strategy Define and lead end-to-end architecture for enterprise GenAI platforms and use cases Design scalable agentic systems (single-agent, multi-agent, orchestration frameworks) Establish reference architectures, design patterns, and reusable frameworks Lead architecture decisions on RAG vs fine-tuning vs hybrid approaches Conduct technology evaluations (LLMs, vector DBs, orchestration frameworks) and recommend best-fit solutions Agentic AI & LLM Engineering Leadership Design and implement complex agentic workflows with tool calling, function orchestration, and memory strategies Build enterprise-grade RAG pipelines with strong focus on retrieval accuracy and evaluation Drive prompt architecture standards (prompt libraries, chaining, orchestration governance) Optimise solutions for latency, cost, scalability, and reliability Platform & Engineering Excellence Lead development of GenAI platforms, APIs, and microservices (FastAPI, Flask, etc.) Define engineering best practices: coding standards, testing, packaging, observability Ensure seamless integration with enterprise data platforms, APIs, and business applications Collaborate with MLOps teams for CI/CD, deployment pipelines, versioning, and monitoring Governance, Risk & Responsible AI Define and enforce LLM guardrails (hallucination control, safety filters, policy enforcement) Implement evaluation frameworks (RAG evaluation, prompt testing, benchmarking) Ensure compliance with data security, privacy, and enterprise governance standards Drive adoption of Responsible AI practices (bias mitigation, explainability, auditability) Data & Ecosystem Collaboration Partner with Data Engineering teams on: - Data ingestion, pipelines, and quality controls Metadata management and knowledge graph strategies Work with business stakeholders to: - Identify high-value GenAI use cases Translate business problems into AI-driven solutions Leadership & Stakeholder Management Provide technical leadership and mentorship to engineering teams Act as a solution advisor to clients/stakeholders (including pre-sales, PoCs, solutioning) Present architecture and design decisions to senior leadership and CXOs Drive COE initiatives, knowledge sharing, and internal capability building Experience Must-Have Skills & Experience 12–15 years total experience, with 3+ years in GenAI / LLM-based systems Proven experience in leading architecture and delivery of enterprise solutions LLM / GenAI & Agentic Engineering Strong hands-on experience with: - LLMs (Claude, OpenAI, etc.) RAG pipelines and retrieval optimisation GPT + Agentic AI implementation experience Experience with: - LangChain, LangGraph, or similar frameworks Agent orchestration and tool-calling architectures Deep understanding of: - LLM limitations, evaluation, and optimisation strategies Core Engineering Strong Python/Pyspark engineering expertise (production-grade development) with proven API integration experience Deep data analysis experience and handling large volume of data Fabric/Azure Databricks/Snowflake data engineering integration skills Good exposure to: - Cloud platforms (Azure/AWS/GCP) SQL Containers, CI/CD, monitoring Cloud & Platform Hands-on experience with Azure / AWS / GCP Familiarity with: - Containers (Docker/Kubernetes) CI/CD pipelines Monitoring & observability Data / AI Foundations (Mandatory) Prior Experience In One Or More Data Engineering (ETL/ELT, pipelines, orchestration) Data Science / ML lifecycle (especially NLP) Analytics engineering / data products Good-to-Have / Preferred Fine-tuning techniques (LoRA, PEFT, prompt tuning) Experience with Azure AI stack (Azure OpenAI, Cognitive Search) Knowledge of knowledge graphs, semantic layers, or enterprise search Experience in domain-specific GenAI solutions (Insurance, BFSI, Healthcare)
More at EXL