Job Title: AI/ML Engineer – Agentic AI
Experience: 5–10+ Years
Employment Type: Full-Time
Location: [Location]
Job Summary
We are seeking a highly skilled AI/ML Engineer with expertise in Agentic AI to design, develop, and deploy intelligent autonomous AI systems for enterprise applications. The ideal candidate will have strong experience with Large Language Models (LLMs), agent frameworks, Retrieval-Augmented Generation (RAG), and cloud-native AI solutions. You will be responsible for building production-ready AI agents capable of reasoning, planning, tool usage, memory management, and autonomous decision-making while ensuring scalability, security, and responsible AI practices.
Key Responsibilities
- Design, build, and deploy autonomous AI agents capable of multi-step reasoning, planning, task execution, and dynamic decision-making.
- Develop intelligent agent workflows using frameworks such as LangGraph, LangChain, Semantic Kernel, AutoGen, CrewAI, or similar technologies.
- Build custom agent orchestration layers with support for tool calling, memory management, retries, guardrails, and execution safety.
- Develop enterprise-grade Retrieval-Augmented Generation (RAG) solutions using vector databases and embedding models.
- Design short-term and long-term memory systems for AI agents, including conversational, semantic, and episodic memory.
- Integrate AI agents with enterprise applications, APIs, CRM, ERP systems, databases, and SaaS platforms.
- Implement planning, reflection, feedback, and self-correction mechanisms to improve agent reliability.
- Optimize prompts using advanced prompt engineering techniques including Chain-of-Thought, Self-Reflection, Few-shot, and Zero-shot prompting.
- Evaluate AI agents using task success metrics, latency, cost, safety, and hallucination detection frameworks.
- Deploy AI applications using Docker, Kubernetes, and cloud-native services on Azure, AWS, or GCP.
- Implement observability, tracing, logging, monitoring, prompt versioning, and CI/CD pipelines for AI systems.
- Ensure responsible AI practices including explainability, privacy, security, prompt injection mitigation, and human-in-the-loop workflows.
- Collaborate with product managers, data scientists, software engineers, and business stakeholders to deliver enterprise AI solutions.
Required Qualifications
- Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Machine Learning, Data Science, or a related field.
- 5–10+ years of software engineering or AI/ML development experience.
- Strong expertise in Python programming.
- Solid understanding of asynchronous programming, concurrency, and distributed systems.
- Hands-on experience building production AI applications using Large Language Models.
- Experience working with OpenAI, Azure OpenAI, Anthropic, or open-source LLMs.
- Strong understanding of autonomous agent architectures including ReAct, Plan-and-Execute, Reflexive Agents, Multi-Agent Systems, and Tool-Using Agents.
- Experience implementing function calling, agent memory, planning, and orchestration workflows.
- Hands-on experience with LangChain, LangGraph, Semantic Kernel, AutoGen, CrewAI, or equivalent frameworks.
- Experience implementing Retrieval-Augmented Generation (RAG) architectures.
- Experience working with vector databases such as FAISS, Pinecone, Azure AI Search, Weaviate, ChromaDB, or Milvus.
- Strong understanding of prompt engineering techniques and LLM optimization.
- Experience integrating AI solutions with REST APIs, enterprise systems, and databases.
- Knowledge of SQL and NoSQL databases.
- Experience deploying AI workloads using Docker and Kubernetes.
- Strong experience with Azure (preferred), AWS, or Google Cloud Platform.
- Understanding of MLOps, AgentOps, CI/CD pipelines, monitoring, and model lifecycle management.
Preferred Qualifications
- Experience with fine-tuning LLMs and parameter-efficient tuning techniques such as LoRA.
- Knowledge of knowledge graphs and hybrid memory architectures.
- Experience with enterprise copilots and AI assistants.
- Familiarity with event-driven architectures and message queues.
- Experience implementing AI safety, guardrails, prompt injection protection, and secure tool execution.
- Knowledge of reinforcement learning for agent optimization.
- Experience with multi-agent collaboration and autonomous workflow orchestration.
Technical SkillsProgramming
- Python
- Async Programming
- Concurrency
- Task Scheduling
AI & Machine Learning
- Large Language Models (LLMs)
- Prompt Engineering
- Agentic AI
- Autonomous AI Agents
- Retrieval-Augmented Generation (RAG)
- Embeddings
- Fine-Tuning (LoRA)
- AI Evaluation Frameworks
Agent Frameworks
- LangGraph
- LangChain
- Semantic Kernel
- AutoGen
- CrewAI
Vector Databases
- FAISS
- Pinecone
- Azure AI Search
- Weaviate
- ChromaDB
- Milvus
Cloud & DevOps
- Microsoft Azure (Preferred)
- AWS
- Google Cloud Platform
- Docker
- Kubernetes
- CI/CD
- Git
Databases & Integration
- SQL
- NoSQL
- REST APIs
- Enterprise Applications (CRM, ERP)
- SaaS Integrations
MLOps & AgentOps
- Prompt Versioning
- Model Versioning
- Monitoring
- Logging
- Tracing
- Observability
Security & Responsible AI
- Prompt Injection Protection
- Guardrails
- Secure Tool Execution
- Explainable AI
- Responsible AI
- Human-in-the-Loop Systems
Preferred Soft Skills
- Strong analytical and problem-solving abilities.
- Excellent communication and collaboration skills.
- Ability to design scalable enterprise AI architectures.
- Passion for emerging AI technologies and continuous learning.
- Ability to work effectively in cross-functional Agile teams.
Work Location: Hybrid remote in Noida, Uttar Pradesh (Noida)
