We are seeking a skilled AI Engineer to build, deploy, and optimize agent-based AI solutions leveraging Large Language Models (LLMs). This role blends software engineering with modern Generative AI practices, enabling LLMs to interact with tools, APIs, and enterprise systems in secure, scalable production environments.
Key Responsibilities:
Design, develop, and test autonomous AI agents and multi-agent systems
Implement RAG pipelines, prompt chains, and tool/function-calling logic
Optimize LLM performance including latency, cost, and hallucination reduction
Build and deploy production-grade AI services and APIs using Python
Integrate AI agents with enterprise systems, data platforms, and external APIs
Implement guardrails, security, monitoring, and observability for AI systems
Debug and resolve non-deterministic AI behavior using tracing tools
Document architectures, prompts, workflows, and evaluation results
Collaborate in an Agile environment to deliver sprint commitments
Contribute to AI experimentation, innovation, and roadmap discussions
Required Skills & Qualifications:
Bachelor’s degree or equivalent practical experience
2+ years of IT or software engineering experience
Strong proficiency in Python (mandatory); Java experience is a plus
Hands-on experience with LLMs and Generative AI fundamentals
Experience with agentic frameworks (LangChain, LangGraph, or similar)
Understanding of RAG architectures, embeddings, and vector stores
Experience building and consuming RESTful APIs
Strong debugging, problem-solving, and communication skills
Preferred Skills:
Advanced prompt engineering techniques (Chain-of-Thought, ReAct, Tree of Thoughts)
Experience designing agent memory systems (short-term and long-term)
Knowledge of LLMOps, evaluation pipelines, and AI observability
Experience with vector databases (Pinecone, Milvus, Weaviate)
Familiarity with CI/CD pipelines and Infrastructure-as-Code