Lead Generative AI Engineer

AI Engineer

Key Responsibilities

• Translate business problems into AI solutions, define acceptance criteria, and deliver iteratively with Product, Architecture, and Data Engineering teams.
• Build

  LLM-powered applications

  (chat, copilots, content generation, workflow assistants) using

  Azure OpenAI

  (GPT family, embeddings) with

  Prompt Flow/AI Studio

  for orchestration.
• Implement

  RAG pipelines

  : document ingestion, chunking,

  vector indexing on Azure AI Search

  , hybrid semantic+keyword retrieval, reranking, and grounding with enterprise sources (SharePoint/Blob/Cosmos/SQL).
• Integrate

  Azure Cognitive Services

  (Document Intelligence, Vision, Speech, Translator) to enrich multimodal solutions.
• Develop secure APIs/services (FastAPI/Flask/.NET/Node) and frontends integrating Entra ID (Azure AD) authentication.
• Operationalize models on

  Azure ML

  (managed endpoints/AKS), establish

  model registries

  , automated CI/CD via

  Azure DevOps

  , tracking with

  MLflow

  , and

  blue/green/Canary

  deployments.
• Implement

  observability & evaluation

  : telemetry (App Insights), offline/online eval, safety metrics, drift detection, human-in-the-loop review, and continuous prompt/model optimization.
• Ensure

  cost governance

  (quotas, rate limits, token budgets), scalability (GPU/CPU pools, autoscaling), and performance SLAs.
• Apply

  Responsible AI

  guardrails: input/output filtering, PII/PHI detection, content safety, red-teaming, and

  risk assessments

  .
• Create

  technical design docs

  , architecture diagrams, runbooks, and handover artifacts.

Required Technical Qualifications;

• Programming:

  Strong Python; familiarity with

  TypeScript/Node

  or

  C#

  is a plus.

• Azure AI:

  Hands-on with

  Azure OpenAI

  ,

  Azure AI Studio/Prompt Flow

  ,

  Azure AI Search (vector)

  ,

  Azure Document Intelligence

  ,

  Azure ML

  (training, managed endpoints),

  AKS

  /

  ACI

  ,

  Functions

  ,

  Event Grid

  .

• RAG & LLM Tools:

  Practical experience with

  LangChain

  /

  LlamaIndex

  (Azure toolchains), embeddings, retrieval evaluation, and prompt engineering.

• Data & Integration:

  Working knowledge of

  Azure Blob/Data Lake

  ,

  Cosmos DB/SQL

  ,

  Data Factory/Synapse

  ; designing pipelines for ingestion and ETL/ELT.

• MLOps:

  CI/CD on

  Azure DevOps

  , experiment tracking (

  MLflow

  ), model governance, monitoring/alerting (

  App Insights/Azure Monitor

  ).

vector DBs