Artificial Intelligence Engineer

Neptron Technologies; Hyderabad; On-site; INR 1,800,000 - 3,200,000; Full time

Job summary

Neptron Technologies in Hyderabad is seeking an AI/ML Engineer focused on agentic AI to join our onsite team. The role demands 6–8 years of experience and hands-on mastery of Python for ML, async programming, and systems design.

You will work across LLMs, agent architectures such as ReAct and Plan-and-Execute, and tool integration, with emphasis on memory, planning, and safe orchestration in production environments.

Qualifications

• Strong programming and systems skills for ML in Python.
• Experience with async programming, concurrency, and task scheduling.
• Hands-on with agentic AI concepts and architectures.
• Familiarity with agent frameworks and tooling (LangGraph/LangChain, Semantic Kernel, AutoGen).

Skills

Python for ML

Async programming

Concurrency

Task scheduling

Tools

LangGraph/ LangChain

Semantic Kernel

AutoGen

Job description

Job Role: AI/ML Engineer (Agentic AI Focus)

Experience: 6 - 8 Years

Location: Hyderabad

Work Mode: 5 Days Onsite

Working Hours: 11 AM 9 PM

Notice Period: Immediate to 15 Days

JD-

1. Core Programming & Systems Skills

• Python (expert level) for ML, orchestration, and agent logic.
• Strong understanding of async programming, concurrency, and task scheduling.

2. Foundations of Agentic AI

• Design and implementation of autonomous AI agents capable of:
• Multi-step reasoning and planning.
• Goal decomposition and task orchestration.
• Dynamic decision-making under uncertainty.
• Experience with agent architectures:
• ReAct.
• Plan-and-Execute.
• Reflexive agents.
• Hierarchical / multi-agent systems.
• Tool-augmented and function-calling agents.
• Understanding of stateful vs. stateless agents and memory management.

3. Large Language Models (LLMs)

• Hands-on experience with LLMs:
• OpenAI.
• Azure OpenAI.
• Anthropic.
• Open-source models.
• Prompt-engineering techniques for:
• Reasoning (Chain-of-Thought, Self-Reflection).
• Planning and critique loops.
• Instruction following and tool use.
• Experience with:
• Few-shot and zero-shot prompting.
• Model selection trade-offs (latency, cost, context length).
• Knowledge of fine-tuning / adapters (LoRA) is a plus.

4. Agent Frameworks & Tooling

• Practical experience with agent frameworks, such as:
• LangGraph / LangChain (agents, tools, memory).
• Semantic Kernel.
• AutoGen, CrewAI, or similar.
• Ability to build custom agent orchestration layers beyond frameworks.
• Tool abstraction and execution safety:
• Timeouts.
• Retries.
• Sandboxing.

5. Memory, Context & Knowledge Augmentation

• Design of agent memory systems:
• Short-term (conversation/state memory).
• Long-term (episodic, semantic memory).
• Retrieval-Augmented Generation (RAG):
• Vector databases (FAISS, Pinecone, Azure AI Search, etc.).
• Embedding selection and chunking strategies.
• Techniques for context management and compression.
• Knowledge graph–augmented or hybrid memory is a plus.

6. Planning, Reasoning & Control

• Experience implementing:
• Task planners (step planning, re-planning).
• Constraint-based execution.
• Feedback and self-correction loops.
• Understanding of:
• Tool reliability scoring.
• Guardrails and action validation.
• Failure detection and graceful recovery.

7. MLOps & AgentOps

• Deployment of agents into production environments.
• Observability for agents:
• Tracing agent decisions and tool calls.
• Logging prompts, responses, and errors.
• Model and prompt versioning.
• CI/CD for agent systems.
• Experience with Docker, Kubernetes, serverless deployments (Azure/AWS).

8. Evaluation & Testing of Agentic Systems

• Designing evaluation frameworks for agents:
• Task success rate.
• Cost, latency, and reliability.
• Safety and hallucination detection.
• Offline test harnesses and simulation environments.
• A/B testing of prompts, tools, and agent strategies.

9. Security, Safety & Responsible AI

• Secure tool execution and privilege control.
• Prompt-injection and jailbreak risk mitigation.
• Data privacy and isolation in agent memory.
• Responsible AI practices:
• Bias awareness.
• Explainability of agent decisions.
• Human-in-the-loop escalation patterns.

10. Data & Integration Skills

• Integration with:
• Enterprise systems (CRM, ERP, databases).
• Web services, internal APIs, and SaaS tools.
• Working knowledge of:
• SQL / NoSQL databases.
• Event-driven systems and message queues is a plus.

11. Cloud & Platform Expertise

• Strong experience with at least one cloud platform:
• Azure (preferred for enterprise agentic AI).
• AWS.
• GCP.
• Managed AI services, identity & access, and secrets management.
• Cost optimization for LLM-driven systems.

12. Bonus / Advanced Skills (Nice to Have)

• Multi-agent collaboration and negotiation.
• Human-AI collaboration patterns (copilots, supervisors).
• Reinforcement learning for agent policy optimization.
• Experience building enterprise copilots or autonomous workflows.