Agentic AI specialists

Company Description

Bosch Global Software Technologies Private Limited

• 5 to 8 years of experience as Data Scientist· 2 to 3 years of experience in Generative AI solution development· Strong understanding of AI agent collaboration, negotiation, and autonomous decision-making.
• Experience in developing and deploying AI agents that operate independently or collaboratively in complex environments.
• Deep knowledge of agentic AI principles, including self-improving, self-organizing, and goal-driven agents.
• Proficiency in multi-agent frameworks such as AutoGen, LangGraph, LangChain, and CrewAI for orchestrating AI workflows.
• Hands-on experience integrating LLMs (GPT, LLaMA, Mistral, etc.) with agentic frameworks to enhance automation and reasoning.
• Expertise in hierarchical agent frameworks, distributed agent coordination, and decentralized AI governance.
• Strong grasp of memory architectures, tool use, and action planning within AI agents.
• Autonomy Score: Measures the degree of independence in decision-making.
• Collaboration Efficiency: Evaluates the ability of agents to work together and share information.
• Task Completion Rate: Tracks the percentage of tasks successfully executed by agents.
• Response Time: Measures the latency in agent decision-making and execution.
• Adaptability Index: Assesses how well agents adjust to dynamic changes in the environment.
• Resource Utilization Efficiency: Evaluates computational and memory usage for optimization.
• Explainability & Interpretability Score: Ensures transparency in agent reasoning and outputs.
• Error Rate & Recovery Time: Tracks failures and the system’s ability to self-correct.
• Knowledge Retention & Utilization: Measures how effectively agents recall and apply information.
• Hands-on experience with LLMs such as GPT, BERT, LLaMA, Mistral, Claude, Gemini, etc.
• Proven expertise in both open-source (LLaMA, Gemma, Mixtral) and closed-source (OpenAI GPT, Azure OpenAI, Claude, Gemini) LLMs.
• Advanced skills in prompt engineering, tuning, retrieval-augmented generation (RAG), reinforcement learning (RAFT), and LLM fine-tuning (PEFT, LoRA, QLoRA).
• Strong understanding of small language models (SLMs) like Phi-3 and BERT, along with Transformer architectures.
• Experience working with text-to-image models such as Stable Diffusion, DALL·E, and Midjourney.
• Proficiency in vector databases such as Pinecone, Qdrant for knowledge retrieval in agentic AI systems.
• Deep understanding of Human-Machine Interaction (HMI) frameworks within cloud and on-prem environments.
• Strong grasp of deep learning architectures, including CNNs, RNNs, Transformers, GANs, and VAEs.
• Expertise in Python, R, TensorFlow, Keras, and PyTorch.
• Hands-on experience with NLP tools and libraries: OpenNLP, CoreNLP, WordNet, NLTK, SpaCy, Gensim, Knowledge Graphs, and LLM-based applications.
• Proficiency in advanced statistical methods and transformer-based text processing.
• Experience in reinforcement learning and planning techniques for autonomous agent behavior. Mandatory Skills:
• Design, develop, test, and deploy Machine Learning models using state-of-the-art algorithms with a strong focus on language models.
• Strong understanding of LLMs, and associated technologies like RAG, Agents, VectorDB and Guardrails· Hand-on experience in GenAI frameworks like LlamaIndex, Langchain, Autogen, etc.
• Experience in cloud services like Azure, GCP and AWS· Multi-agent frameworks: AutoGen, LangGraph, LangChain, CrewAI· Large Language Models (LLMs): GPT,
  

Qualifications