Principal Architect AI Data Engineer

Lead the design of enterprise-grade GenAI and agentic architectures (single-agent, multi-agent, tool-driven systems).

Define reference architectures, reusable frameworks, and best practices for LLM applications across the organisation.

Architect and oversee implementation of end-to-end RAG pipelines : Data ingestion → chunking → embeddings → vector search → orchestration → response synthesis.

Data ingestion → chunking → embeddings → vector search → orchestration → response synthesis.

Drive scalability, reliability, cost optimisation, and performance across GenAI platforms.

Provide technical leadership in prompt engineering, prompt orchestration, and agent workflows (LangChain, LangGraph, etc.).

Guide teams on tool-calling, function-calling, memory handling, and multi-agent system design .

Lead efforts in hallucination reduction, guardrails, safety mechanisms, and output evaluation frameworks .

Architect production-grade APIs and services (FastAPI/Flask/enterprise microservices) for LLM solutions.

Define MLOps / LLMOps pipelines including CI/CD, monitoring, observability, and evaluation.

Partner with Data Engineering teams to ensure: Data quality, lineage, governance, and compliance Seamless integration with enterprise data platforms

Data quality, lineage, governance, and compliance

Seamless integration with enterprise data platforms

Build and scale GenAI / Agentic AI Centre of Excellence (CoE) .

Define standardised frameworks, accelerators, and reusable components to improve delivery velocity.

Drive organisation-wide adoption of GenAI best practices and tooling standards .

Engage with CXOs, business stakeholders, and clients to translate business problems into AI-led solutions.

Lead solutioning, pre-sales, RFP responses, and client workshops for GenAI opportunities.

Influence AI strategy, roadmap, and investment decisions at organisational level.

Establish enterprise governance frameworks for GenAI: Responsible AI, security, privacy, ethical usage, and compliance

Responsible AI, security, privacy, ethical usage, and compliance

Define policies for: Data access, redaction, model usage, auditability, and explainability

Data access, redaction, model usage, auditability, and explainability

Mentor and guide architects, engineers, and data scientists .

Drive technical upskilling, hiring strategy, and capability maturity .

Review solution designs and enforce architecture quality standards .

15+ years of total experience in Data Engineering / Data Science / AI

3+ years of hands-on experience in LLM / GenAI solutions at scale

Proven experience in architecture, solution design, and enterprise delivery

Strong hands-on experience with: LLMs (Claude, OpenAI, etc.) RAG pipelines and retrieval optimisation GPT + Agentic AI implementation experience

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

LangChain, LangGraph, or similar frameworks

Agent orchestration and tool-calling architectures

Deep understanding of: LLM limitations, evaluation, and optimisation strategies

LLM limitations, evaluation, and optimisation strategies

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 platforms (Azure/AWS/GCP)

SQL

Containers, CI/CD, monitoring

Prior experience in one or more:

Data Engineering (ETL/ELT, pipelines, orchestration)

Data Science / ML lifecycle (especially NLP)

Analytics engineering / data products

Fine-tuning techniques ( LoRA, PEFT, prompt tuning, few-shot learning )

Experience with enterprise GenAI deployments (security, privacy, governance)

Experience with Azure ecosystem (Azure OpenAI, AI Search, Fabric, etc.)

Exposure to industry use cases (Insurance, BFSI, Healthcare, Retail, etc.)