Job Summary :
We are seeking a highly skilled and experienced Senior Generative AI Engineer to lead the development of intelligent agents powered by advanced generative AI models. In this role, you will be responsible for designing, implementing, and optimizing AI-driven agents that interact naturally with users and systems. You will collaborate with cross-functional teams to bring cutting-edge generative models to life, with a strong emphasis on Python programming, machine learning, and deep learning.
Key Responsibilities :
- Design, build, and optimize generative AI agents for use in complex applications and workflows.
- Develop and fine-tune LLM-based (e.g., GPT, LLaMA, Mistral) agents for autonomous or semi-autonomous decision-making and task execution.
- Write robust, scalable Python code to support AI pipelines, model serving, and agent orchestration.
- Integrate various ML and deep learning techniques to enhance agent capabilities, including memory, reasoning, and tool usage.
- Leverage frameworks such as LangChain and LlamaIndex build and chain agent actions.
- Work with structured and unstructured data sources (e.g., text, embeddings, knowledge graphs) to train and inform agents.
- Collaborate with product managers, data scientists, and software engineers to deploy agent-based systems into production environments.
- Stay updated on the latest research and trends in GenAI, LLMs, and autonomous agents.
Requirements : Must-Have :
5+ years of experience in software development, with at least 2–3 years in machine learning or deep learning.Strong proficiency in Python and AI / ML libraries such as PyTorch, TensorFlow, Hugging Face Transformers, etc.Experience building or customizing generative models (text generation, summarization, question answering).Proven experience developing AI agents using frameworks like LangChain, CrewAI, AutoGen, etc.Solid understanding of LLM architecture, prompt engineering, and retrieval-augmented generation (RAG).Familiarity with orchestration tools and APIs for tool-use and multi-agent coordination.Experience with model fine-tuning, embeddings, vector databases (e.g., FAISS, Weaviate), and serving ML models in production.Strong problem-solving skills, ability to work independently and in a team.Nice-to-Have :
Experience with multi-modal AI (text + vision / audio).Familiarity with reinforcement learning or human-in-the-loop systems.Contributions to open-source GenAI tools or frameworks.MLOps experience : model deployment, monitoring, and scaling.Tools & Technologies Required
Programming & Frameworks :
Python – Primary language for AI development (Required)PyTorch / TensorFlow – Deep learning frameworks (Required)Hugging Face Transformers – For using and fine-tuning LLMs (Required)LangChain / CrewAI / AutoGen / Haystack – For building LLM-powered agents (Required)LLM & NLP :
OpenAI GPT (e.g., GPT-4 / GPT-4o), Anthropic Claude, LLaMA, Mistral, Mixtral, or similar – Familiarity with both proprietary and open-source LLMs (Required)Prompt engineering and optimization – Crafting and refining system and user prompts (Required)RAG (Retrieval-Augmented Generation) pipelines (Required)Data & Vector Search :
Vector Databases : FAISS, Weaviate, Pinecone, Chroma (Required)Embeddings APIs : OpenAI, Hugging Face, Cohere (Required)Oracle DBModel Deployment & MLOps :
FastAPI / Flask – For serving models as APIs (Required)Docker / Kubernetes – Containerization and orchestration (Nice-to-Have)MLflow / Weights & Biases – Model tracking and experiment management (Nice-to-Have)Orchestration & Tool Use :
Agent Frameworks : LangGraph, Semantic Kernel, or similar (Required)Tool Calling APIs : OpenAI function calling, Toolformer-like tool integration (Required)DevOps & Infrastructure :
Git / GitHub – Version control (Required)Cloud platforms : AWS, GCP, Azure – Especially for GPU / TPU access (Nice-to-Have)CI / CD tools – GitHub Actions, Jenkins (Nice-to-Have)Other Helpful Tools :
VSCode / Jupyter Notebooks – Development environments (Required)