AI Platform Engineer — Bots & AI Agents

Role Overview

We are looking for an AI Platform Engineer with hands-on experience building, deploying, and scaling AI-powered bots, copilots, and autonomous agents. The ideal candidate combines strong software engineering skills with practical experience in LLMs, agentic AI, RAG, tool calling, APIs, and AI platforms.

You will be responsible for designing and developing AI systems that can understand user intent, reason over information, use tools/APIs, execute workflows, and interact with users autonomously.

Key Responsibilities

• Design, build, and deploy AI bots, conversational assistants, copilots, and autonomous AI agents.
• Develop agent workflows using LLMs, function/tool calling, agent frameworks, and orchestration platforms.
• Build RAG (Retrieval-Augmented Generation) systems using vector databases and enterprise knowledge sources.
• Integrate AI agents with REST APIs, databases, SaaS applications, internal platforms, and enterprise systems.
• Develop multi-step agent workflows capable of planning, reasoning, executing actions, and handling failures.
• Build reusable AI platform components, APIs, SDKs, and services that can support multiple AI applications.
• Implement prompt engineering, context management, memory, guardrails, evaluation, and observability.
• Deploy AI applications to cloud environments and design for scalability, reliability, security, and performance.
• Monitor AI agents in production and improve accuracy, latency, cost, and reliability.
• Work with product, engineering, data, and business teams to identify opportunities for AI automation.
• Establish best practices for LLM evaluation, model selection, prompt/version management, and responsible AI.

Required Skills

AI / LLM

• Strong hands-on experience with Generative AI and Large Language Models (LLMs).
• Experience building AI bots and autonomoagentic systems.
• Experience with:
  • RAG
  • Prompt engineering
  • Function/tool calling
  • Agent memory and context management
  • LLM evaluation
  • AI guardrails
  • Structured outputs
• Experience with models such as OpenAI, Anthropic, Gemini, Llama, or similar.

Agent Frameworks

Experience with one or more:

• LangChain / LangGraph
• LlamaIndex
• Semantic Kernel
• AutoGen
• CrewAI
• Microsoft Copilot / Azure AI
• Other agent orchestration frameworks

Software Engineering

• Strong Python development skills.
• Experience developing production-grade APIs and microservices.
• Strong understanding of REST APIs, JSON, authentication, databases, and distributed systems.
• Experience with SQL and/or NoSQL databases.
• Experience with Git, CI/CD, testing, and software engineering best practices.

AI Platform / Cloud

• Experience deploying AI applications on AWS, Azure, or Google Cloud Platform.
• Familiarity with Docker and Kubernetes.
• Experience with vector databases such as Pinecone, Weaviate, Milvus, Qdrant, pgvector, or equivalent.
• Understanding of observability, logging, monitoring, security, and cost optimization for AI workloads.

Preferred Qualifications

• Experience building multi-agent systems.
• Experience integrating AI agents with enterprise applications and APIs.
• Experience building production chatbots or virtual assistants.
• Experience with streaming LLM responses and real-time conversational systems.
• Knowledge of model fine-tuning, embeddings, reranking, and model evaluation.
• Experience with AI security, prompt injection protection, data privacy, and access control.
• Experience taking AI prototypes from POC to production.