Full stack Engineer Generative & Agentic AI

Location:

About the Role

AI/ML Engineer

Key Responsibilities

• Design, build, and deploy AI/ML solutions with a focus on

  Generative AI (LLMs, RAG)

  and

  Agentic AI architectures

  .
• Implement vector-based semantic search and retrieval pipelines using

  Pinecone, Weaviate, ChromaDB, or OpenSearch

  .
• Develop, optimize, and evaluate LLM-based applications, including

  prompt and context engineering

  .
• Integrate AI/ML solutions with

  cloud platforms

  (GCP Vertex AI, AWS Bedrock, or equivalent).
• Collaborate with cross-functional teams to understand business requirements and translate them into AI-driven solutions.
  
• Contribute to building

  data pipelines and MLOps workflows

  to ensure scalable and reliable AI deployments.
• Research, prototype, and integrate emerging frameworks for

  multi-agent systems, orchestration, and reasoning

  .
• Document processes, best practices, and share knowledge across the team.
  

Key Skills

• Generative AI & LLMs

  : RAG architectures, prompt engineering, context optimization.

• Agentic AI

  : Agent architectures, planning, reasoning, tool-use, multi-agent orchestration.

• Programming & Frameworks

  : Python, LangChain, LlamaIndex, Hugging Face.

• Vector Databases

  : Pinecone, Weaviate, ChromaDB, OpenSearch.

• Cloud AI Platforms

  : GCP Vertex AI, AWS Bedrock (or similar services).

• MLOps & Pipelines

  : Data pipelines, deployment, and model lifecycle basics.

• Evaluation & Optimization

  : RAGAS, A/B testing, HITL evaluation frameworks.

• Fine-Tuning & Adaptation

  : Domain-specific model training, memory systems for conversational AI.

• Tooling & Productivity

  : GitHub Copilot, Cursor, modern AI development tools.

• Collaboration & Communication

  : Ability to translate technical concepts for non-technical stakeholders.

Must-Have Qualifications

• 35 years of professional experience in AI, ML, Data Science, or Automation.
  
• Hands-on experience with

  Generative AI (LLMs, RAG)

  and/or

  Agentic AI

  .
• Strong

  Python

  programming skills; experience with LangChain, LlamaIndex, Hugging Face.
• Familiarity with

  cloud AI services

  (GCP Vertex AI, AWS Bedrock).
• Understanding of

  data pipelines

  and

  MLOps practices

  .
• Experience in

  prompt/context engineering

  for LLMs.
• Knowledge of

  vector databases

  .
• Awareness of

  agent architectures

  (planning, reasoning, tool-use).
• Problem-solving mindset and eagerness to learn.
  
• Strong teamwork and communication skills.
  

Good-to-Have Qualifications

• Experience with

  LangGraph, Google ADK, CrewAI, Semantic Kernel

  .
• Exposure to

  multi-agent systems

  .
• Experience with

  fine-tuning/adapting foundation models

  .
• Knowledge of

  evaluation frameworks

  (RAGAS, HITL evaluation).
• Conversational AI memory systems.
  
• Productivity tools like

  GitHub Copilot, Cursor

  .
• Function calling, tool integration, and API orchestration.
  
• Certifications in AI/ML (Azure, AWS, GCP).
  
• Domain knowledge in

  finance, accounting, or ERP systems

  .

Interview Process

two technical rounds

1. Round 1 Online Technical Interview (90 mins)

• Focus: Problem-solving, Python coding, ML fundamentals, Generative AI concepts, and applied case scenarios.
  
• Format: Discussion of past projects and AI system design.
  

2. Round 2 Onsite Technical Interview (2–3 hrs)

• Focus: Deep dive into

  Generative/Agentic AI projects

  , architecture design, hands-on problem-solving, and whiteboarding.
• Includes evaluation of ability to work in teams, communicate technical solutions, and handle real-world challenges.
  

Why Join Us?

• Work on

  cutting-edge AI solutions

  in Generative and Agentic AI.
• Opportunity to contribute to

  innovative multi-agent systems

  at scale.
• Collaborative, learning-driven team culture.
  
• Competitive compensation and career growth opportunities.