Agentic Engineer
Job Fit Check
Base Career helps you apply smarter for this job.
Key skills for this role
About the Role
Bell Integration seeks an Agentic Engineer to design, build, and operate production-grade agentic AI systems. You will work with LLM orchestration, MCP/A2A tool connectivity, RAG, evaluation, observability, safety, and cost optimization.
Key Skills for This Role
Responsibilities
- Design, build and operate production grade agentic AI systems that can reason, use tools, maintain state, and retrieve knowledge
- Select and integrate appropriate LLMs and agent frameworks across Azure OpenAI, Anthropic, and open models
- Engineer reliable tool use patterns including function calling, structured outputs, MCP servers, and API wrappers
- Implement retrieval, memory and context engineering patterns including RAG pipelines, hybrid search, and summarization
- Own agent evaluation, safety and observability: automated evals, red team testing, prompt injection defenses, and dashboards
- Optimize performance and commercial viability through token budgeting, prompt caching, model routing, and cost monitoring
Requirements
- Experience designing and building production grade agentic AI systems
- Proficiency in LLM orchestration frameworks (LangChain, LlamaIndex, Azure Semantic Kernel)
- Strong knowledge of RAG pipelines, hybrid search, and context engineering
- Experience with tool integration and function calling
- Familiarity with prompt caching, token budgeting, and cost optimization
- Knowledge of safety and guardrails for LLM applications
Full Job Posting
Agentic Engineer Overview
- Production agentic AI systems, LLM orchestration, MCP/A2A tool connectivity, RAG, evaluation, observability, safety and cost optimisation.
- Design, build and operate production grade agentic AI systems that can reason, use tools, maintain state, retrieve knowledge, execute multi step workflows and escalate safely to humans.
- Select and integrate appropriate LLMs and agent frameworks across Azure OpenAI, Anthropic, open models and provider native agent SDKs.
- Engineer reliable tool use patterns including function calling, structured outputs, MCP servers, API wrappers, permissions, retries, timeouts, sandboxing and audit trails.
- Implement retrieval, memory and context engineering patterns including RAG pipelines, hybrid search, re ranking, short term and long term memory, summarisation and context budgeting.
- Own agent evaluation, safety and observability: automated evals, golden datasets, red team testing, prompt injection defences, PII controls, traceability, dashboards and production feedback loops.
- Optimise performance and commercial viability through token budgeting, prompt caching, model routing, batching, cost monitoring and continuous improvement of agent success rates.
Agent Architecture & Design
- Define agent workflows: goals, tools, decision loop.
- Choose orchestration framework: LangChain, LlamaIndex, Azure Semantic Kernel, or custom agent loop.
- Design tool interfaces: functions, parameters, expected response format.
- Implement error handling: recovery, escalation to human.
- Design multi turn conversations: context window management, prevent infinite loops.
LLM Selection & Prompting
- Evaluate models for use case: latency, cost, context window.
- Write system prompts: role definition, task boundaries, safety guidelines.
- Implement few shot prompting and chain of thought.
- Test prompt robustness against jailbreak attempts and adversarial inputs.
Tool Integration & Function Calling
- Define tool schemas: functions agents can call.
- Implement tool wrappers: validate inputs, execute safely, return structured responses.
- Implement guardrails: rate limit, permissions, audit logging.
- Handle tool failures: retry logic, fallback tools.
- Optimize tool calls: batch calls, cache results.
Prompt Caching & Cost Optimization
- Implement prompt caching to save tokens.
- Batch requests when possible.
- Use cheaper models for certain tasks.
- Implement token counting and monitor API costs.
Safety & Guardrails
- Implement input validation: filter adversarial prompts.
- Implement output filtering: prevent PII leakage.
- Handle refusals with clear explanations.
- Audit logging for all agent interactions.
- Implement human in the loop for sensitive actions.
Performance & Observability
- Monitor agent latency and breakdown by LLM call, tool execution, parsing.
- Track accuracy metrics and compare model versions.
- Implement observability: log structured data to Azure Application Insights.
Apply for this job in 1 click
Skip the repetitive application forms
Install the Base Career Chrome Extension and autofill job applications across major job boards with your profile.
Trusted by over 500,000 job seekers on Base Career
More from this employer
More jobs at Bell Integration United Arab Emirates
FDE Engineer
, UAE
Bell Integration seeks an FDE Engineer to design Azure infrastructure, own CI/CD pipelines, and ensure deployment excellence. You will work directly with clients to understand business needs and shape AI solutions. Requi
Quality Guardian
, UAE
Bell Integration seeks a Quality Guardian to ensure zero critical/high bugs reach production. You will design test plans, build automated test suites, perform manual and exploratory testing, and drive quality best practi
POD Full stack Engineer
Abu Dhabi, UAE
Bell Integration is seeking a POD Full Stack Engineer with 6+ years of experience to build and deliver enterprise solutions in Dubai. The role requires strong frontend and backend skills, experience with Azure, Oracle, a
POD Captain
Abu Dhabi, UAE
Bell Integration is seeking a POD Captain to lead cross-functional software delivery teams in Dubai. The role requires 8+ years in software delivery or engineering leadership, with experience managing agile teams and cli