AI Engineer

Job Description:
Agentic AI Engineer (2+Years Experience) Role Overview

We are seeking an experienced Agentic AI Engineer to design, build, and evolve scalable agent-based AI applications and platforms. This role requires strong hands-on expertise in distributed system design, and modern agentic AI frameworks to deliver autonomous, production-grade AI systems.

You will work closely with product, data, and engineering teams to architect and implement intelligent agent workflows, LLM pipelines, and memory-driven reasoning systems in a cloud-agnostic environment.

• Implement agent-based systems, including orchestration, planning, execution, and memory management
• Build and deploy LLM-driven pipelines, including prompt strategies, tool invocation, and retrieval-augmented generation (RAG)
• Design vector-based memory systems and hybrid retrieval mechanisms (vector + keyword + structured data)
• Drive technical decisions related to architecture, tooling, and infrastructure, ensuring performance, reliability, and extensibility
• Partner with Data Scientist to develop and optimize ML models, pipelines, and orchestration logic for real-world use cases
• Collaborate within Agile teams to deliver high-quality, production-ready solutions

• 2 years of industry experience in AI/ML and Intelligent systems development
• Proven experience delivering AI or ML solutions in large-scale or enterprise environments

• Strong understanding of Agentic AI architectures, including both neural-based and symbolic agents
• Hands-on experience building multi-agent systems, including:
  • Agent collaboration and coordination
  • Reinforcement learning or feedback-driven optimization
  • Dynamic or flexible workflows
  • State, caching, and memory management
• Experience with one or more agentic AI frameworks, such as:
  • Lang Graph / Lang Chain
  • CrewAI
  • Semantic Kernel
  • Auto Gen or equivalent frameworks

• Strong proficiency in Python for building scalable, production-grade systems
• Experienced or foundational knowledge in machine learning frameworks such as Tensor Flow, PyTorch, Scikit-learn, or AutoML tools
• Solid understanding of model lifecycle management, including training, evaluation, and deployment

• Practical experience with prompt engineering techniques, including:
  • Zero-shot and few-shot prompting
  • Chain-of-thought and structured reasoning
  • Prompt iteration and optimization
• Experience building LLM-based applications, including tool use and function calling

• Experience designing and implementing Information Retrieval (IR) and RAG systems
• Hands-on work with vector databases, embeddings, and optionally knowledge graphs
• Familiarity with hybrid search approaches (vector + lexical + metadata-based retrieval)

• Experience evaluating AI systems using quantitative and qualitative metrics
• Familiarity with A/B testing, benchmarking, and performance analysis of LLMs and prompts

• Programming
  
  Languages:
  
  Python (required)
• Agentic AI:
  Lang Graph, Lang Chain, CrewAI, Semantic Kernel, Auto Gen, OpenAI Agent SDK, or similar
• Generative AI: LLMs, RAG architectures, NLP pipelines
• Cloud Platforms:
  Experience with at least one major cloud provider (e.g., GCP, Azure, AWS); ability to design cloud-agnostic architectures
• Version Control:
  Git / Git Hub
• Development Practices:
  Model testing, validation, CI/CD awareness
• Collaboration:
  
  Experience working in Agile / Scrum teams

• The candidate independently designs and implements enterprise-grade agentic AI solutions with minimal supervision and zero hand-holding.
• Translates ambiguous or loosely defined business requirements into well-architected, scalable, and production-ready agentic systems.
• Delivers solutions that adhere to enterprise IT, security, and compliance standards, including data governance and access controls.
• Builds fault-tolerant, resilient agentic software, with clear handling of both success and failure scenarios.
• Implements comprehensive testing strategies, covering positive paths, edge cases, and failure modes, incorporating explicit business validation inputs.
• Proactively collaborates with cross-functional team members to promote shared learning, technical excellence, and best practices.
• Acts as a reliable team contributor during high-pressure situations, including production incidents or critical system failures, supporting root-cause analysis and rapid recovery.
• Demonstrates ownership, accountability, and a production-first mindset throughout the lifecycle of agentic AI solutions.