AI Engineer (Generative AI/ Agents)

Job Description

We are looking for a highly skilled AI Agent Engineer / Generative AI Engineer with hands-on experience in building and deploying enterprise-grade Generative AI and AI Agent solutions using AWS Bedrock as the primary platform and Google Gemini / Vertex AI Agent Builder as a secondary ecosystem.

The ideal candidate should have strong expertise in AI workflow orchestration, prompt engineering, tool calling, guardrails, conversation memory management, and evaluation frameworks for LLM-powered applications.

This role requires a blend of backend engineering, GenAI architecture, and AI product thinking to build scalable, secure, and observable AI systems for enterprise use cases.

Key Responsibilities

AI Agent Development

- Design, develop, and deploy AI agents using Amazon Web Services Bedrock.
- Build multi-step agentic workflows with tool calling, orchestration logic, and contextual reasoning.
- Integrate external APIs, enterprise systems, databases, and knowledge sources into AI workflows.
- Prompt Engineering & Orchestration

- Develop advanced prompt orchestration frameworks for reliable and scalable AI interactions.
- Optimize prompts for accuracy, latency, safety, and cost efficiency.
- Implement prompt chaining, contextual retrieval, and response grounding techniques.

Tool Calling & Workflow Design

- Build structured tool-calling frameworks for enterprise AI applications.
- Design agent workflows involving function calling, task decomposition, and autonomous execution patterns.
- Develop reusable orchestration pipelines for AI-driven automation.

Guardrails & AI Safety

- Design and implement AI safety policies, moderation layers, and governance mechanisms.
- Create guardrails for hallucination control,



prompt injection prevention, and secure AI responses.
- Ensure responsible AI practices and enterprise compliance standards.

Conversation Memory & Session Management

- Implement short-term and long-term conversation memory architectures.
- Design session handling and context persistence for conversational AI systems.
- Optimize memory retrieval and contextual continuity for multi-turn interactions.

AI Evaluation & Observability

- Build evaluation pipelines for LLM performance testing and benchmarking.
- Monitor AI application performance including latency, token usage, hallucination rates, and response quality.
- Implement observability frameworks, logging, tracing, and feedback loops for AI systems.

Cloud & Deployment

- Deploy scalable AI services on AWS infrastructure.
- Work closely with DevOps and backend teams for production-grade deployment and monitoring.
- Contribute to architecture discussions and platform optimization.

Required Skills & Qualifications

Mandatory Skills

- 4-8 years of overall software engineering or AI application development experience.
- Minimum 1+ years of hands-on experience with Amazon Web Services Bedrock/Vertex AI.
- Strong understanding of Generative AI, LLMs, and AI Agent architectures.

- Experience in:
- Prompt orchestration
- Tool calling and workflow design
- AI guardrails and policy frameworks
- Conversation memory/session handling
- AI evaluation and observability

- Solid experience with Python and API integrations.
- Understanding of vector databases, embeddings, and RAG architectures.
- Familiarity with REST APIs, microservices, and cloud-native systems.

Education

- Bachelors or Masters degree in Computer Science, Artificial Intelligence, Data Science, or related field.

📌 AI Engineer (Generative AI/ Agents) (Noida)
🏢 Omnie Solutions
📍 Noida