AI Agentic Engineer

Location: Remote
Experience: 6+ years
Positions: 1
Employment Type: Full-time

Job Overview

We are looking for an experienced AI Agentic Engineer to design, develop, and deploy production-grade AI agents and autonomous workflows. The ideal candidate will have strong Python and LLM expertise, hands-on experience with agent frameworks, RAG, orchestration, evaluation, and cloud deployment, with a strong focus on enterprise-grade reliability and security.

Key Responsibilities

- Design and develop autonomous AI agents capable of multi-step reasoning, planning, task decomposition, and dynamic decision-making.
- Build agent architectures using ReAct, Plan-and-Execute, Reflexive, hierarchical, and multi-agent patterns.
- Develop tool-augmented and function-calling agents with secure tool execution.
- Implement agent memory, state management, context management, and long-term knowledge retention.
- Build and optimize RAG pipelines using vector databases, embeddings, chunking, retrieval, and hybrid search.
- Develop planning, re-planning, feedback, self-correction, and graceful-recovery mechanisms.
- Integrate LLMs from OpenAI, Azure OpenAI, Anthropic, and open-source ecosystems.
- Build agent orchestration using LangGraph/LangChain, Semantic Kernel, AutoGen, CrewAI, or custom orchestration frameworks.
- Implement observability, tracing, logging, model/prompt versioning, and production monitoring.
- Design evaluation frameworks covering task success, reliability, latency, cost, hallucination, and safety.
- Implement security controls for prompt injection, jailbreaks, data isolation, privilege management, and safe tool execution.
- Integrate agents with enterprise applications, databases, APIs, SaaS platforms, CRM/ERP systems, and event-driven services.
- Deploy and operate agentic applications using cloud platforms and modern DevOps practices.





Required SkillsProgramming & Systems

- Expert-level Python programming.
- Robust understanding of asynchronous programming, concurrency, task scheduling, and distributed execution.
- Strong SQL/NoSQL and API integration experience.

Agentic AI

- Strong hands-on experience building production AI agents.
- Knowledge of:
- ReAct
- Plan-and-Execute
- Reflexive agents
- Hierarchical and multi-agent architectures
- Tool/function calling
- Stateful and stateless agents
- Agent memory management

LLMs & Prompt Engineering

- Practical experience with OpenAI, Azure OpenAI, Anthropic, or open-source LLMs.
- Strong prompt-engineering skills for reasoning, planning, critique, reflection, and tool use.
- Experience with few-shot and zero-shot prompting.
- Understanding of model selection based on cost, latency, context window, and performance.
- Knowledge of LoRA/adapters and fine-tuning is a plus.

Frameworks & Tooling

- Hands-on experience with one or more:
- LangGraph / LangChain
- Semantic Kernel
- AutoGen
- CrewAI
- Ability to build custom agent orchestration beyond off-the-shelf frameworks.
- Experience implementing timeouts, retries, sandboxing, validation, and execution safety.

RAG & Memory

- Experience designing short-term and long-term agent memory.
- Strong RAG experience with technologies such as FAISS, Pinecone, Azure AI Search, or equivalent.
- Understanding of embeddings, chunking, retrieval strategies, context compression, and hybrid/knowledge-graph-based retrieval.





MLOps / AgentOps

- Experience deploying AI/ML applications into production.
- Knowledge of agent tracing, observability, prompt/response logging, and error monitoring.
- Experience with Docker and Kubernetes.
- Exposure to serverless and cloud-native deployments.
- CI/CD and model/prompt versioning experience.

Cloud

- Strong experience with at least one major cloud platform:
- Azure — preferred
- AWS
- GCP
- Experience with managed AI services, IAM, secrets management, and cloud cost optimization.

Evaluation, Security & Responsible AI

- Experience designing offline evaluation and simulation frameworks for agentic systems.
- Ability to measure task success rate, cost, latency, reliability, and safety.
- Experience with A/B testing of prompts, tools, models, and agent strategies.
- Understanding of prompt-injection and jailbreak mitigation.
- Knowledge of secure tool execution, access control, privacy, and data isolation.
- Experience implementing human-in-the-loop escalation and responsible AI practices.

Good to Have

- Multi-agent collaboration and negotiation.
- Enterprise copilots and autonomous workflow automation.
- Human-AI collaboration and supervisor/copilot patterns.
- Knowledge graphs and hybrid memory architectures.
- Reinforcement learning for agent policy optimization.
- Experience with event-driven systems and message queues.

What We're Looking For

- Strong problem-solving and system-design skills.
- Ability to take an AI agent solution from concept to production.
- Strong understanding of enterprise AI architecture and operational reliability.
- Comfortable working with rapidly evolving LLM and agentic AI technologies.
- Strong communication and collaboration skills.

Pay: ₹200,000.00 - ₹220,000.00 per month

Work Location: Remote

📌 AI/ML Engineer - Agentic AI Focus (India)
🏢 Delphic Global
📍 India