Generative AI Engineer

The selected candidate will be working for our Indian JV - D2AI Labs.

The location is Bangalore/Chennai/Remote.

Responsibilities

Key Responsibilities:

•⁠ ⁠Lead Agent Development: Architect, build, and deploy the central interface agent that connects and coordinates specialized AI agents.

•⁠ ⁠Agent Orchestration: Implement reliable communication, delegation, and data-handling mechanisms between agents.

•⁠ ⁠LLM Integration: Fine-tune and integrate LLMs (Azure OpenAI or similar), utilizing advanced prompt engineering techniques.

•⁠ ⁠MLOps Implementation: Maintain robust MLOps pipelines, CI/CD workflows, and performance monitoring on Azure.

•⁠ ⁠Vector Database Management: Design data pipelines using vector databases like Pinecone, Qdrant, or Milvus for RAG and agent memory.

•⁠ ⁠A2A Communication & MCP: Enable advanced agent-to-agent communication using established protocols like MCP/MCPTx.

•⁠ ⁠Collaborate with cross-functional teams to translate business requirements into scalable AI/ML solutions.

•⁠ ⁠Optimize AI models for performance, scalability, and accuracy.

•⁠ ⁠Conduct thorough testing, evaluation, and documentation of models and systems.

•⁠ ⁠Stay up to date with the latest advancements in AI, particularly in the Generative AI space.

Qualifications & Skills

•⁠ ⁠Proven experience in LLM model development (e.g., OpenAI, GPT, BERT, etc.).

•⁠ ⁠Hands-on experience in building GenAI agents and conversational workflows.

•⁠ ⁠Strong Python programming skills with a focus on AI/ML libraries and frameworks (e.g., PyTorch, TensorFlow, Hugging Face).

•⁠ ⁠Proven experience building or orchestrating multi-agent systems using frameworks like LangGraph.

•⁠ ⁠Prior work experience in the Telecom industry with a clear understanding of domain-specific challenges.