Artificial Intelligence Engineer

Senior AI EngineerLocation: Gurugram, IndiaCompany OverviewTheHireHub.ai is a recruiter-first AI hiring platform built by recruitment professionals with over 20+ years of industry experience. Designed to automate and elevate the entire hiring lifecycle, the platform leverages a multi-agent AI architecture to manage job creation, sourcing, outreach, screening, evaluation, interview scheduling, and analytics. TheHireHub.ai combines applied AI, workflow automation, and human-in-the-loop intelligence to help organizations hire faster, smarter, and with higher precision.Role OverviewWe are seeking a Senior AI Engineer to design, build, and scale the AI systems that power TheHireHub.ai’s multi-agent recruiting platform. This role focuses on architecting intelligent workflows using large language models (LLMs), retrieval systems, and agent orchestration frameworks to deliver production-grade AI capabilities across hiring use cases.You will be responsible for building end-to-end AI pipelines that enable autonomous and semi-autonomous agents to reason, evaluate candidates, generate outreach, manage screening, and support decision-making—while ensuring performance, cost efficiency, and reliability at scale.Key ResponsibilitiesArchitect and implement LLM-driven multi-agent systems for recruitment workflows including job analysis, candidate matching, outreach, screening, and evaluation.Design and maintain modular AI pipelines combining retrieval, reasoning, scoring, and response generation layers.Build and orchestrate agent workflows using frameworks such as LangChain, LangGraph, and Model Context Protocol (MCP).Develop scalable backend APIs and microservices to expose AI capabilities across the platform.Implement and optimize Retrieval-Augmented Generation (RAG) pipelines using vector databases and embedding models.Evaluate, fine-tune, and deploy open-source and proprietary models for text and structured data tasks.Optimize AI systems for latency, throughput, token usage, and cost efficiency.Collaborate closely with product, backend, frontend, and data teams to embed AI features into user-facing workflows.Build internal tooling to accelerate experimentation, prompt iteration, agent evaluation, and deployment.Stay current with emerging AI research, frameworks, and agent architectures to guide platform evolution.Essential Skills & TechnologiesCore AI & MLStrong hands-on experience with LLMs (OpenAI GPT, Anthropic Claude, Llama, Mistral, Gemini, DeepSeek, etc.).Deep understanding of prompt engineering, function calling, tool use, and context management.Experience building agent-based systems using LangChain, LangGraph, and MCP (Model Context Protocol).Solid understanding of RAG architectures, vector databases (Pinecone, Weaviate, FAISS, Chroma), and embedding strategies.Familiarity with model fine-tuning, evaluation, and serving using frameworks like Hugging Face, vLLM, or Ollama.Engineering & ArchitectureStrong proficiency in Python (FastAPI preferred); Node.js experience is a plus.Experience designing microservices, async systems, and event-driven architectures.Cloud deployment experience (AWS, GCP, Azure, or serverless environments).Databases: MongoDB / PostgreSQL / Redis.Strong understanding of API design, security, and scalable system architecture.Optimization & ObservabilityExperience optimizing AI systems for latency, reliability, and cost.Token usage management and cost optimization for LLM-based workflows.Monitoring, logging, and tracing using tools such as Prometheus, Grafana, ELK, or OpenTelemetry.Additional PlusExperience with LangServe, LlamaIndex, Haystack, or Autogen frameworks.Exposure to multi-agent reasoning, evaluation matrices, or autonomous workflows.Familiarity with MLOps tools (MLflow, Kubeflow, Weights & Biases).Understanding of multimodal AI (documents, resumes, structured hiring data).Frontend exposure (React / TypeScript) for integrating AI-driven UX.What You’ll Bring5+ years of experience building and deploying AI/ML systems in production environments.Strong background in NLP, generative AI, or applied machine learning.Ability to balance innovation with system performance, reliability, and scalability.Strong engineering fundamentals and experience shipping real-world AI products.A builder’s mindset—curious, hands-on, and driven to create high-impact AI systems.

Apply Now