Job Title: AI/ML Engineer – Agentic AI
Experience: 5–10 Years
Employment Type: Full-Time
Location: Remote / Hybrid
Department: Artificial Intelligence & Machine Learning
Role Summary
We are looking for an experienced AI/ML Engineer with strong expertise in Agentic AI, Large Language Models (LLMs), and intelligent autonomous systems. The ideal candidate will design, develop, and deploy AI agents capable of multi-step reasoning, planning, tool usage, and autonomous decision-making. You will work closely with AI researchers, product teams, and software engineers to build enterprise-grade AI solutions that leverage modern agent frameworks, Retrieval-Augmented Generation (RAG), and cloud-native architectures. This role emphasizes expertise in Agentic AI frameworks, production-ready AI systems, and scalable LLM-powered applications.
Key ResponsibilitiesAgentic AI Development
- Design, develop, and deploy autonomous AI agents capable of planning, reasoning, and task execution.
- Implement agent architectures such as ReAct, Plan-and-Execute, Reflexive Agents, and Multi-Agent Systems.
- Build intelligent workflows using tool-augmented agents and function-calling capabilities.
- Develop custom orchestration layers for enterprise AI applications.
Large Language Models (LLMs)
- Integrate and optimize LLMs including OpenAI, Azure OpenAI, Anthropic, and open-source models.
- Design advanced prompt engineering strategies for reasoning, planning, self-reflection, and tool utilization.
- Evaluate model performance based on latency, accuracy, cost, and context limitations.
- Fine-tune models using techniques such as LoRA (preferred).
Retrieval-Augmented Generation (RAG)
- Design and implement RAG pipelines for enterprise knowledge retrieval.
- Build and optimize vector search solutions using FAISS, Pinecone, Azure AI Search, or similar vector databases.
- Develop efficient embedding, chunking, indexing, and retrieval strategies.
- Implement memory systems for both short-term and long-term conversational context.
Agent Frameworks & Orchestration
- Develop AI applications using LangGraph, LangChain, Semantic Kernel, CrewAI, AutoGen, or similar frameworks.
- Build reusable agent orchestration components beyond framework capabilities.
- Implement secure tool execution, retries, timeout handling, and sandboxing.
Planning & Autonomous Decision-Making
- Develop AI systems capable of:
- Goal decomposition
- Task planning and re-planning
- Constraint-based execution
- Self-correction and feedback loops
- Implement guardrails, validation mechanisms, and failure recovery strategies.
MLOps & AgentOps
- Deploy AI agents into production environments.
- Build CI/CD pipelines for AI and agent-based systems.
- Implement observability, tracing, prompt logging, monitoring, and model versioning.
- Optimize deployment using Docker, Kubernetes, and cloud-native services.
Enterprise Integration
- Integrate AI agents with:
- CRM
- ERP
- Databases
- Enterprise APIs
- SaaS platforms
- Develop secure API integrations and event-driven workflows.
- Collaborate with engineering teams to build scalable AI-powered enterprise solutions.
Responsible AI & Security
- Implement responsible AI practices including explainability, bias mitigation, and human-in-the-loop workflows.
- Protect AI systems against prompt injection, jailbreak attacks, and unauthorized access.
- Ensure secure memory management and enterprise data privacy.
Required Technical SkillsProgramming
- Expert-level Python
- Asynchronous Programming
- Concurrency & Task Scheduling
Agentic AI
- Autonomous AI Agents
- Multi-Agent Systems
- ReAct
- Plan-and-Execute
- Reflexive Agents
- Tool Calling
- Function Calling
- Agent Orchestration
Large Language Models
- OpenAI
- Azure OpenAI
- Anthropic
- Open-source LLMs
- Prompt Engineering
- Chain of Thought (CoT)
- Self-Reflection
- Few-shot & Zero-shot Prompting
- LoRA (Preferred)
AI Frameworks
- LangChain
- LangGraph
- Semantic Kernel
- CrewAI
- AutoGen
RAG & Knowledge Systems
- Retrieval-Augmented Generation (RAG)
- Vector Databases (FAISS, Pinecone, Azure AI Search)
- Embeddings
- Semantic Search
- Chunking Strategies
- Memory Management
MLOps & Cloud
- Docker
- Kubernetes
- Azure (Preferred)
- AWS
- GCP
- CI/CD
- AgentOps
- Model Versioning
- Observability & Monitoring
Data & Integration
- REST APIs
- SQL / NoSQL
- Enterprise Integrations
- Event-Driven Architecture
- Message Queues
Preferred Qualifications
- Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Machine Learning, Data Science, or a related field.
- 5–10 years of experience in AI/ML engineering or software engineering with a focus on AI.
- Experience developing production-grade LLM or Agentic AI applications.
- Experience building enterprise copilots, AI assistants, or autonomous workflows.
- Azure AI Engineer, Azure AI Fundamentals, AWS AI/ML, or equivalent certifications are a plus.
Soft Skills
- Strong analytical and problem-solving abilities.
- Excellent communication and stakeholder management skills.
- Ability to work independently in a fast-paced Agile environment.
- Strong collaboration with cross-functional engineering and product teams.
- Passion for AI innovation and continuous learning.
- Ownership mindset with attention to quality and scalability.
Nice-to-Have Skills
- Multi-agent collaboration and negotiation.
- Reinforcement Learning (RL) for agent optimization.
- Human-AI collaboration patterns.
- Knowledge Graphs and Graph RAG.
- AI safety, explainability, and governance.
- Enterprise Copilot development.
- Cost optimization for LLM-based systems.
Work Location: Hybrid remote in Noida, Uttar Pradesh (Noida)
