Job Summary

Demand Unit Name : Agentic AI Engineer II – Agent Orchestration & RAG Workflows

Band : E2.1

Target : Engineering Graduates from Tier 1 Institutions (IIT, NIT, DTU)

Purpose of the Role:

The Agentic AI Engineer II will contribute to the design, development, and optimization of agentic AI systems, multi-agent orchestration frameworks, and advanced Retrieval-Augmented Generation (RAG) workflows. The role focuses on building intelligent, autonomous agents capable of reasoning, planning, and interacting across enterprise systems while ensuring robust performance, accuracy, and scalability.
As high-potential engineers from premier institutions, they will work closely with senior architects and AI teams to deliver next-generation AI capabilities for real-world enterprise applications.

Key Responsibilities

Responsibilities :

1. Develop and enhance agentic workflows using LLM-based agents, decision-making loops, and orchestration frameworks.
2. Implement and optimize RAG pipelines including document ingestion, chunking strategies, embedding generation, vector search, and retrieval ranking.
3. Build and maintain reusable components for agent orchestration frameworks (state management, tool invocation, memory modules, guardrails).
4. Assist in constructing multi-agent systems that collaborate, negotiate, and coordinate tasks for complex enterprise workflows.
5. Work with senior engineers to integrate agents with APIs, microservices, and enterprise platforms for end-to-end automation.
6. Contribute to experimentation, evaluation, and benchmarking of agent behavior, retrieval quality, and task success rates.
7. Participate in full lifecycle engineering: design discussions, code reviews, testing, and documentation.
8. Troubleshoot issues, analyze logs and outputs, and propose improvements to reliability and performance.
9. Continuously learn emerging AI techniques, frameworks, and best practices to elevate solution maturity.

Skill Requirements

Technical Skills

Must Have :

• Strong programming skills in Python
• Strong fundamentals in algorithms, data structures, distributed systems, and software engineering.
• Solid understanding of LLMs, prompt engineering concepts, and reasoning frameworks.
• Familiarity with modern AI/ML libraries (PyTorch, TensorFlow).
• Exposure to LLM frameworks such as LangChain, LlamaIndex, or similar orchestration tools.
• Understanding of vector databases (FAISS, Pinecone, Milvus, Weaviate) and embedding models.
• Basic experience with REST APIs, microservices, and event-driven systems.
• Familiarity with retrieval systems, text processing, and information extraction techniques.
• Understanding of cloud environments (Azure/AWS/GCP) and containerization basics (Docker).

Other Requirements

Desirable :

• Exposure to autonomous agent frameworks (e.g., ReAct, Reflexion, AutoGen, CrewAI).
• Knowledge of RLHF concepts, tool-using agents, and planning algorithms.
• Experience in building small AI projects, hackathon prototypes, or research PoCs.
• Familiarity with CI/CD, Kubernetes, MLflow, experiment tracking, or observability tools.
• Understanding of advanced RAG enhancements (rerankers, hybrid search, graph-based retrieval, query rewriting).

Behavioral Competencies :

• Strong analytical thinking, curiosity, and eagerness to explore emerging AI technologies.
• Ability to learn rapidly and apply concepts to real-world engineering problems.
• Collaborative mindset with openness to feedback, mentorship, and peer learning.
• High sense of ownership and responsibility for assigned tasks.
• Clear communication and documentation skills.
• Adaptability and resilience in fast-paced, evolving project environments.
• Passion for innovation, research, and continuous improvement.