The Agentic AI Engineer is responsible for designing, building, and deploying intelligent, AI agents capable of reasoning, planning, and executing complex tasks across business and technical domains. This role focuses on production‑grade agentic systems powered by Large Language Models (LLMs), integrated with enterprise tools, APIs, and data sources.
This is a hands-on role requiring end‑to‑end ownership — from agent architecture and development through deployment, monitoring, evaluation, and continuous optimization. The ideal candidate combines strong software engineering fundamentals with deep expertise in LLM application design, agent frameworks, Retrieval‑Augmented Generation (RAG), memory systems, and multi‑agent orchestration.
In addition to strong engineering skills, this role requires a product mindset—partnering with business stakeholders to shape use cases, select appropriate agentic tools and frameworks, and translate user needs into scalable technical solutions..
Key Responsibilities
- Agent Architecture & Development
- Design and implement agentic AI architectures, including:
- ReAct (Reason + Act)
- Plan‑and‑Execute
- Tool‑using agents
- Multi‑agent systems and coordinators
- Build LLM‑powered applications using modern foundation models
- Translate business use cases into reliable, scalable agent workflows with clear handoffs and fallbacks
- LLM & RAG Engineering
- Develop and optimize prompt engineering strategies for reasoning, task execution, and tool use.
- Implement Retrieval‑Augmented Generation (RAG) pipelines using structured and unstructured data.
- Design and manage agent memory systems, including:
- Short‑term (conversation/state)
- Long‑term (vector‑based memory)
- Work with vector databases
- Tooling, APIs & Integration
- Build and integrate internal and external tools (APIs, microservices, enterprise systems).
- Enable agents to safely interact with:
- Databases
- Business applications
- Automation platforms
- Cloud services
- Ensure robust error handling, retries, and fallback logic.
- Production Readiness & Operations
- Deploy agentic systems into production environments.
- Implement monitoring, logging, and evaluation frameworks for:
- Accuracy and task success
- Latency and cost efficiency
- Safety and policy compliance
- Design and enforce guardrails to prevent hallucinations, unsafe actions, or data leakage.
- Continuously optimize system performance and cost
- Collaboration & Delivery
- Partner closely with business stakeholders, application developers, data teams, and business stakeholders.
- Act as a technical product owner for agentic solutions: collect user and business requirements, clarify problem statements, and translate them into system designs and implementation plans
- Identify high‑impact AI opportunities and rapidly prototype, validate, and scale solutions.
- Contribute to internal best practices, architecture standards, and AI governance.
- Lead agentic tooling decisions: evaluate frameworks, model providers, orchestration patterns, and integration approaches; make pragmatic build/buy choices aligned to security, reliability, and cost constraints.
- Act as a technical product partner: collect user requirements, define success metrics and acceptance criteria, translate needs into solution designs and implementation plans, and drive delivery from prototype to production.
- Required Qualifications
- Bachelor's degree in Computer Science, Computer Engineering, Information Technology, or equivalent experience.
- 3+ years of professional software development experience.
- Strong proficiency in Python (required).
- Hands‑on experience working with LLM APIs, and MCP
- Solid understanding of:
- Prompt engineering
- Embeddings and semantic search
- Retrieval‑Augmented Generation (RAG)
- API and backend system design
- Experience integrating AI systems into production applications.
- Familiarity with cloud platforms (Azure, AWS, or GCP).
- Strong problem‑solving skills and ability to manage multiple priorities in fast‑paced environments.
- Excellent written and verbal communication skills in English
- Preferred / Nice‑to‑Have Skills
- Experience with agent frameworks (e.g., LangChain, Semantic Kernel, AutoGen, CrewAI).
- Knowledge of multi‑agent coordination patterns.
- Experience with evaluation frameworks for LLMs and agents.
- Exposure to security, privacy, and compliance considerations in AI systems.
- Familiarity with CI/CD pipelines and DevOps practices.
- Experience building AI solutions for enterprise or internal business use cases
- What Success Looks Like
- Full‑time role: on‑site.
- Collaboration with global or cross‑functional teams may require flexible working hours.
- Strong emphasis on ownership, experimentation, and delivery.
- Work Environment:
- Works in a standard office environment utilizing standard office equipment.
- Works in team and individual environments.
- May work weekends and overtime when necessary.
- Ability to travel as needed, both domestic and international
