Summary
We are seeking a highly motivated AI Engineer to design, build, and deploy AI agents and multi-agent systems. This role focuses on bridging traditional software engineering with Generative AI, enabling LLMs to interact with tools, APIs, and enterprise data systems.
The ideal candidate will have hands-on experience with RAG, LLMs, cloud platforms (AWS/Google Cloud Platform), and agentic frameworks, along with strong Python development skills.
Key Responsibilities
AI Agent Development
- Design and develop AI agents and multi-agent systems
- Build prompt workflows, chains, and implement tool/function calling
- Work on RAG (Retrieval-Augmented Generation) pipelines
- Perform testing for non-deterministic AI outputs
Performance Optimization
- Optimize LLM performance (latency, token usage, cost)
- Reduce hallucinations and improve response accuracy
- Debug and troubleshoot agent workflows
Full-Stack AI Development
- Develop scalable backend systems using Python
- Integrate AI models with APIs and enterprise systems
- Implement guardrails and security controls
AI/ML Engineering Practices
- Apply LLMOps, evaluation pipelines, and monitoring
- Manage vector databases like Pinecone, Milvus, Weaviate
- Implement CI/CD and infrastructure-as-code practices
System Integration
- Integrate AI agents with internal systems and third-party APIs
- Enable agents to perform real-world actions beyond text generation
Debugging & Monitoring
- Analyze agent behavior using tools like LangSmith, Arize
- Diagnose failures, loops, and unpredictable outputs
Documentation & Collaboration
- Document agent workflows, prompts, and architectures
- Work in an Agile environment with cross-functional teams
Required Qualifications
- Bachelor's degree or equivalent experience
- 2+ years of IT engineering experience
- Strong proficiency in Python
- Experience with REST APIs development and integration
- Understanding of LLM concepts:
- Context Windows
- Temperature
- Embeddings
- Vector Databases
- Hands-on experience with:
- RAG (Retrieval-Augmented Generation)
- LLMs (Large Language Models)
- Cloud Platforms: AWS or Google Cloud Platform
- Familiarity with:
- LangChain, LangGraph, or similar agent frameworks
Preferred Qualifications
- Experience with Java
- Advanced Prompt Engineering techniques (ReAct, Chain-of-Thought, etc.)
- Knowledge of AI agent memory systems
- Experience building AI evaluation frameworks
- Strong understanding of system design with AI components
- Exposure to multi-agent architectures
