AI/ML Engineer – Agentic AI

Job Summary

We are looking for an AI/ML Engineer – Agentic AI with strong expertise in Python, LLMs, LangGraph/LangChain, RAG, multi-agent systems, and prompt engineering.

The role focuses on building and deploying autonomous AI agents, enterprise copilots, and intelligent workflows using Azure/AWS, Docker, Kubernetes, MLOps, and AgentOps, with a strong focus on scalability, security, observability, and responsible AI.

Technical Skill Set – Agentic AI

- Core Programming & Systems

Expert-level Python for ML, orchestration, and agent development

Strong understanding of asynchronous programming, concurrency, and task scheduling

- Agentic AI

Experience designing autonomous AI agents for multi-step reasoning, planning, task orchestration, and dynamic decision-making

Knowledge of ReAct, Plan & Execute, Reflexive, hierarchical, and multi-agent architectures

Experience with tool-augmented and function-calling agents

Understanding of stateful/stateless agents and memory management

- Large Language Models (LLMs)

Hands-on experience with OpenAI, Azure OpenAI, Anthropic, or open-source LLMs

Solid prompt engineering skills

Experience with few-shot/zero-shot prompting, reasoning, planning, critique loops, and tool usage

Understanding of model selection based on latency, cost, and context requirements

Knowledge of fine-tuning/LoRA is a plus

- Agent Frameworks & Tooling

Hands-on experience with LangGraph/LangChain

Exposure to Semantic Kernel, AutoGen, CrewAI, or similar frameworks

Ability to build custom agent orchestration layers

Experience with tool abstraction, execution safety, retries, timeouts, and sandboxing

- Memory, Context & RAG

Experience designing short-term and long-term agent memory

Strong RAG implementation experience





Knowledge of vector databases such as FAISS, Pinecone, Azure AI Search, etc.

Understanding of embeddings, chunking strategies, context management, and compression

Knowledge of knowledge-graph or hybrid memory approaches is a plus

- Planning, Reasoning & Control

Experience implementing task planning and re-planning

Constraint-based execution and feedback/self-correction loops

Understanding of guardrails, action validation, failure detection, and recovery mechanisms

- MLOps & AgentOps

Experience deploying AI agents into production

Agent observability, tracing, logging, and monitoring

Model and prompt versioning

CI/CD for AI/agent systems

Hands-on experience with Docker, Kubernetes, Azure/AWS, or serverless deployments

- Evaluation & Testing

Experience evaluating agent systems based on task success, cost, latency, reliability, and safety

Experience with offline test harnesses and simulation environments

A/B testing of prompts, tools, and agent strategies

- Security & Responsible AI

Secure tool execution and privilege control

Understanding of prompt injection and jailbreak mitigation

Data privacy and isolation in agent memory

Responsible AI practices, explainability, and human-in-the-loop escalation

- Data & Integration

Integration with enterprise systems, CRM, ERP, databases, APIs, and SaaS platforms

Working knowledge of SQL/NoSQL databases

Exposure to event-driven systems and message queues is a plus

- Cloud & Platform

Strong expertise in at least one cloud platform: Azure, AWS, or GCP

Experience with managed AI services, IAM, secrets management, and security

Understanding of LLM cost optimization

- Nice to Have

Multi-agent collaboration and negotiation

Enterprise copilots and autonomous workflows

Human-AI collaboration patterns

Reinforcement learning for agent policy optimization

📌 AIML with Agentic AI (Hyderabad)
🏢 Prophecy Technologies
📍 Hyderabad