AI Engineer – Agentic Systems & Generative AI
Role Overview
We are hiring an experienced AI Engineer to design and scale next-generation agent-based AI systems that drive intelligent automation and enhance enterprise workflows. This role requires a strong engineering mindset applied to AI agent architecture, with a focus on building reliable, production-grade systems powered by LLMs, retrieval pipelines, and orchestration frameworks.
You will play a key role in shaping how AI-driven solutions are designed, deployed, and scaled across complex environments. This includes defining architectural patterns, selecting the right modeling approach, and ensuring systems meet enterprise expectations for performance, security, and reliability.
Core Responsibilities
Agentic AI Design & Development
- Build and deploy intelligent agents and copilots that integrate with business applications and internal platforms
- Define architectural patterns for single-agent and multi-agent systems, including coordination and communication strategies
- Implement tool-enabled agents using function calling and external integrations
Full Lifecycle AI System Delivery
- Own development from ideation through production deployment
- Select appropriate approaches across:
- Large language models
- Traditional machine learning
- Rule-based logic
- Develop backend services, APIs, and user-facing conversational interfaces
Retrieval & Context Engineering
- Create scalable RAG (Retrieval-Augmented Generation) pipelines
- Design systems for managing context, grounding, and memory
- Optimize retrieval using embeddings, vector search, and ranking techniques
Orchestration & Workflow Engineering
- Develop orchestration layers for multi-step AI workflows
- Build and maintain frameworks for agent coordination and execution
- Reduce risks such as hallucination amplification and cascading failures
Enterprise-Scale Deployment
- Build solutions that are secure, fault-tolerant, and cost-efficient
- Ensure high performance, availability, and observability of AI systems
- Implement monitoring and evaluation methods to track model behavior
Innovation & Prototyping
- Rapidly prototype new AI-driven capabilities and validate feasibility
- Experiment with emerging AI frameworks and architectures
- Transition prototypes into scalable, production-ready systems
Technical Leadership
- Partner with cross-functional teams to deliver impactful solutions
- Provide guidance on AI architecture, tooling, and engineering best practices
- Mentor engineers and contribute to long-term technical strategy
Required Qualifications
Experience & Programming
- 8+ years of experience in:
- Software engineering
- AI/ML engineering
- Distributed systems development
- Strong proficiency in:
- Python (mandatory)
- Additional languages such as Java or similar (preferred)
AI & Machine Learning Expertise
- Hands-on experience deploying LLM-powered applications in production
- Ability to evaluate and choose between:
- LLM-based approaches
- Classical ML models
- Deterministic/rule-based systems
- Understanding of tradeoffs including latency, cost, and accuracy
Agentic AI & LLM Systems
- Experience building:
- AI agents and autonomous systems
- Multi-agent coordination patterns
- Conversational AI applications (chatbots, assistants, copilots)
- Expertise in:
- Prompt design and optimization
- Context management and reasoning workflows
Retrieval & Data Systems
- Strong experience with:
- RAG pipelines and retrieval systems
- Vector databases (e.g., FAISS, Pinecone, Weaviate)
- Embeddings and semantic search
Tools, Frameworks & Architecture
- Familiarity with frameworks such as:
- Experience building:
- API-driven services
- Distributed, microservices-based architectures
- Understanding of orchestration systems and workflow automation
Scalability & Reliability
- Proven ability to design production-grade AI systems at scale
- Expertise in system reliability, observability, and performance tuning
- Experience building secure and resilient architectures
Education
- Bachelor’s or Master’s degree in:
- Computer Science
- Engineering
- Or related technical discipline
Preferred Skills
- Experience with:
- Model Context Protocol (MCP) or similar tool-use frameworks
- AI safety, evaluation, and hallucination mitigation strategies
- Cloud platforms such as AWS, Azure, or Google Cloud Platform
- Strong stakeholder communication and leadership skills
- Track record of mentoring engineers and influencing architecture decisions
- Passion for exploring emerging AI technologies
Agentic AI, AI Engineer, Senior Staff Engineer, Generative AI, GenAI, LLM, Large Language Models, AI Agents, Multi-Agent Systems, RAG, Retrieval Augmented Generation, Prompt Engineering, Context Engineering, LangChain, LlamaIndex, MCP, Model Context Protocol, Python, Machine Learning, ML, Conversational AI, Chatbots, Copilots, Vector Database, Embeddings, Semantic Search, Pinecone, FAISS, Weaviate, AI Orchestration, Workflow Automation, Distributed Systems, Microservices, API Development, AI Architecture, Production AI Systems, AI Platforms, NLP, Deep Learning, Cloud AI, AWS, Azure, Google Cloud Platform
Never miss an opportunity! Create an alert based on the job you applied for.
