Title:  Agentic AI Developer

Area(s) of responsibility

Agentic AI Technical Developer (Must have  - Autogen/CrewAI/LangGraph)

This is not a data science role. This is completely implementation centric role in core AgenticAI application engineering projects  The Implementation Technical Developer will be responsible for designing, developing, and deploying cutting-edge Agentic AI solutions using the latest Large Language Models (LLMs) and frameworks. This role requires deep expertise in Python programming, cloud platforms (Azure, GCP, AWS), and advanced AI techniques such as Agent Patterns, Agent to Agent, MCP, fine-tuning, LLMOps, and Responsible AI. will lead to the development of scalable, secure, and efficient Agentic AI applications, ensuring alignment with business goals and technical requirements.

Required Skills:

1. Python Programming: Deep expertise in Python for building AgenticAI applications and automation tools.
2. LLM Frameworks: Proficiency in frameworks like Autogen/Crew.ai/LangGraph, LlamaIndex, and LangChain.
3. Large-Scale Data Handling & Solution: Design and implement solution for handling large-scale structured and unstructured data.
4. Multi-Modal LLM Applications: Familiarity with text chat completion, vision, and speech models.
5. Fine-tune SLM(Small Language Model) for domain specific data and use cases.
6. Prompt injection fallback and RCE tools such as Pyrit and HAX toolkit etc.
7. Anti-hallucination and anti-gibberish tools such as Bleu etc.
8. Cloud Platforms: Extensive experience with Azure, GCP, and AWS LLM ecosystems and APIs.
9. Fine-Tuning Techniques: Mastery of PEFT, QLoRA, LoRA, and other fine-tuning methods.
10. LLMOps: Strong knowledge of LLMOps practices for model deployment, monitoring, and management.
11. Responsible AI: Expertise in implementing ethical AI practices and ensuring compliance with regulations.
12. RLHF and RAG: Advanced skills in Reinforcement Learning with Human Feedback and Retrieval-Augmented Generation.
13. Modular RAG: Deep understanding of Modular RAG architectures and their implementation.