Agentic AI Engineer

Job description

**About Coforge** - **Coforge is a global** **digital services and solutions provider, specializing in** **digital transformation, cloud, data, and AI-driven solutions** - **The company focuses on key industries such as** **Banking & Financial Services, Insurance, Travel, Transportation & Hospitality** - **Coforge is known for its** **engineering-led approach, strong client partnerships, and emphasis on** **emerging technologies like AI, automation, and cloud modernization** - **With a global delivery model and innovation-driven culture, Coforge provides opportunities to work on** **cutting-edge AI/ML and enterprise-scale digital transformation projects** **Agentic AI Engineer / Data Scientist** ***35 Years Experience • Full-Time*** **Key Responsibilities** - **Design and ship autonomous AI agents with real-world tool use, memory, and multi-step reasoning** - **Build and optimize RAG pipelines from chunking strategies and hybrid search to re-ranking and contextual retrieval** - **Own end-to-end ML pipelines from data ingestion through to model serving at scale** - **Deploy and manage models on AWS Bedrock and AgentCore runtime** - **Engineer prompts and context strategies that push model performance to its limits** - **Instrument MLOps practices — CI/CD, orchestration, monitoring, and model governance — so what you build stays reliable in production** **What will help you to be successful in this role** **Required** - **3–5 years of hands-on experience building production ML or AI systems** - **Strong Python skills and fluency with ML libraries (PyTorch, TensorFlow, Scikit-learn)** - **Deep experience with LLM APIs, embeddings, and vector databases** - **Solid grasp of RAG architectures — chunking, hybrid search, re-ranking, contextual retrieval** - **Hands-on experience building agents with at least one framework:** **Strands, LangGraph, OpenAI Agents SDK, Google ADK, or Azure AI Agent Service** - **Clear understanding of agentic primitives: workflows, tools, short-term and long-term memory** - **Strong prompt engineering and context engineering skills** - **Experience deploying on** **AWS Bedrock** **and** **AgentCore runtime**