Role Overview

We are seeking an Agentic AI Engineer to design, build, and deploy autonomous, goal-driven AI systems (“AI agents”) that can reason, plan, take actions, and collaborate with other systems and agents.

The role focuses on LLM-powered multi-agent architectures, tool use, memory, orchestration, and real-world integration to solve complex business problems at scale.

Key Responsibilities

Agentic System Design & Development

• Design and implement autonomous AI agents using Large Language Models (LLMs)
• Build single-agent and multi-agent systems with planning, reasoning, memory, and tool execution
• Implement agent behaviors such as:
  • Task decomposition and planning
  • Reflection and self-correction
  • Long-term and short-term memory
  • Collaboration and delegation across agents

LLM & AI Engineering

• Integrate and optimize LLMs (e.g., OpenAI, Azure OpenAI, Anthropic, open-source models)
• Apply prompt engineering, structured outputs, function calling, and RAG techniques
• Fine-tune or adapt foundation models where required
• Evaluate and improve model performance, reliability, and hallucination control

Tooling & Orchestration

• Enable agents to safely use tools such as:
  • APIs and microservices
  • Databases (SQL/NoSQL/vector stores)
  • Web search and enterprise systems
• Implement agent frameworks and orchestration layers (e.g., LangGraph, CrewAI, AutoGen, custom frameworks)

Data, Memory & Knowledge Systems

• Design vector-based memory systems using embeddings
• Implement Retrieval-Augmented Generation (RAG) pipelines
• Manage knowledge ingestion, indexing, and lifecycle

Production & Engineering Excellence

• Build scalable, reliable, and secure AI services
• Collaborate with product, platform, and data engineering teams
• Implement monitoring, logging, evaluation, and safety guardrails
• Ensure compliance with data privacy and responsible AI standards

Required Skills & Qualifications

Core Technical Skills

• Strong programming skills in Python (mandatory); JavaScript/TypeScript is a plus
• Hands-on experience building applications with LLMs
• Deep understanding of:
  • Agentic workflows and autonomous systems
  • Prompting strategies and output control
  • RAG architectures and vector databases

AI & ML Knowledge

• Working knowledge of:
  • Transformer-based models
  • Embeddings and semantic search
  • Model evaluation and bias mitigation
• Familiarity with fine-tuning and inference optimization

Systems & Cloud

• Experience with cloud platforms (Azure preferred, AWS/GCP acceptable)
• APIs, microservices, and serverless architectures
• CI/CD, containerization (Docker), and basic MLOps practices

Preferred / Nice-to-Have Skills

• Experience with agent frameworks (LangChain, LangGraph, AutoGen, CrewAI, Semantic Kernel)
• Knowledge of reinforcement learning or planning algorithms
• Experience in enterprise AI adoption or AI governance
• Front-end integration for AI-driven UX (optional)

Soft Skills

• Strong problem-solving and system design skills
• Ability to translate business problems into autonomous AI workflows
• Clear communicator with a collaborative mindset
• Comfort working in fast-evolving, ambiguous problem spaces