AI Agent Developer

Job Description

Role Overview:

We are looking for an AI Agent Developer to design, develop, and deploy intelligent AI agents and agentic workflows that automate business processes and improve user experiences. The ideal candidate should have strong experience with LLMs, prompt engineering, RAG, tool/function calling, APIs, and AI agent frameworks.

Key Responsibilities:

Design and develop production-ready AI agents and multi-agent systems.
Build agentic workflows using LLMs, tools, APIs, memory, and retrieval systems.
Integrate AI agents with internal and external APIs, databases, SaaS platforms, and business applications.
Develop RAG (Retrieval-Augmented Generation) pipelines using vector databases and embedding models.
Implement prompt engineering, structured outputs, function/tool calling, and context management.
Work with frameworks such as LangChain, LangGraph, LlamaIndex, CrewAI, AutoGen, or equivalent technologies.
Integrate models from providers such as OpenAI, Anthropic, Google, or open-source LLMs.
Build evaluation, monitoring, guardrails, and testing systems for AI agents.
Optimize agents for accuracy, latency, reliability, scalability, and cost.
Develop backend services and APIs to support AI applications.
Collaborate with product managers, software engineers, data scientists, and business teams.
Stay current with developments in generative AI, agentic AI, LLMs, and AI engineering.

Required Skills:

Strong programming skills in Python.
Hands-on experience building LLM-powered applications and AI agents.
Experience with REST APIs, JSON, webhooks, and third-party integrations.
Strong understanding of prompt engineering and LLM behavior.
Experience with RAG, embeddings, vector databases, and semantic search.
Knowledge of agent frameworks such as LangGraph/LangChain, LlamaIndex, CrewAI, or similar.
Experience with databases such as PostgreSQL, MongoDB, Redis, or equivalent.
Understanding of cloud platforms such as AWS, Azure, or GCP.
Familiarity with Git, Docker, CI/CD, and production software development practices.
Understanding of AI safety, hallucination mitigation, evaluation, and observability.
Preferred Skills
Experience with multi-agent architectures.
Experience implementing MCP/tool integrations.
Knowledge of AI evaluation and observability platforms.
Experience with fine-tuning or adapting open-source LLMs.
Familiarity with Kubernetes and scalable cloud deployments.
Experience building conversational AI, voice agents, or enterprise copilots.
Knowledge of authentication, authorization, and secure AI application development.
Experience
2–5+ years of software development experience, with 1–3+ years of hands-on experience in Generative AI/LLM application development preferred.

Education:
Bachelor’s or Master’s degree in Computer Science, Engineering, Artificial Intelligence, Data Science, or a related field is preferred.

Key Performance Indicators:

Quality and reliability of deployed AI agents.
Agent accuracy and task-completion rate.
Latency and infrastructure/API cost optimization.
Successful integration with business systems.
Production stability, monitoring, and scalability.
Delivery of AI automation initiatives within agreed timelines.