Lead Agentic AI Engineer

Job Description

We are seeking a Senior Agentic AI Developer with strong Data Engineering

foundations to design, develop, and deploy autonomous AI agent systems for

enterprise-scale use cases. The ideal candidate combines deep expertise in

agentic AI architectures with hands-on experience in data pipelines, LLMs,

and cloud platforms.

Role & responsibilities

- Architect and develop autonomous AI agents capable of executing complex

  business workflows with minimal human intervention.

- Design and maintain ETL/ELT pipelines that process structured and

  unstructured data at scale.

- Build single-agent and multi-agent systems, incorporating planning,

  reasoning, memory management, tool/function calling, and workflow

  orchestration.

- Integrate AI agents with enterprise systems, internal APIs, and third-party

  tools.

- Optimize AI applications for performance, scalability, latency, and cost

  efficiency.

- Implement agent evaluation frameworks, observability tooling, and production

  monitoring.

- Apply Prompt Engineering, Prompt Optimization, and Prompt Chaining to

  improve LLM-driven workflows.

- Implement Retrieval-Augmented Generation (RAG) patterns using semantic

  search, embeddings, and vector databases.

- Ensure LLM reliability through guardrails, hallucination mitigation, and AI

  safety best practices.

- Own the full delivery lifecycle: architect, develop, test, deploy, and

  maintain AI agent solutions from concept to production.

- Collaborate with stakeholders across engineering, product, and business

  teams within Agile delivery frameworks.

Agentic AI & LLMs

-----------------

- Proven experience designing and building agentic AI systems for enterprise

  use cases.

- Expertise in agentic frameworks such as LangGraph, LangChain, CrewAI,

  AutoGen, Semantic Kernel, or equivalent.

- Hands-on experience building GenAI applications using OpenAI, Anthropic,

  Google Gemini, or open-source LLMs (Llama, Mistral, etc.).

- Strong understanding of LLM concepts including RAG, embeddings, vector

  databases, and semantic search.

- Knowledge of LLM evaluation, guardrails, and AI safety best practices.

Data Engineering

----------------

- Strong proficiency in Python and SQL.

- Solid experience designing and operating ETL/ELT pipelines for both

  structured and unstructured data.

- Good to have - Hands-on experience with Databricks and/or Snowflake.

Infrastructure & Delivery

--------------------------

- Experience with cloud platforms: Azure, AWS, or GCP.

- Familiarity with Git, CI/CD pipelines, and Agile methodologies.

- Strong problem-solving, communication, and stakeholder management skills.