AI Engineer (Agentic Systems, Deployment & Infrastructure Sizing)

Role Summary

We are looking for a specialized AI Engineer with deep expertise in architecting, building, and deploying autonomous AI Agents alongside a robust command of the underlying hardware and software infrastructure required to run them efficiently. Unlike purely API-bound developers, you will be responsible for the full stack: designing multi-agent workflows, implementing RAG (Retrieval-Augmented Generation) and tool-use pipelines, and sizing/optimizing the compute infrastructure (GPUs, VRAM, local/on-premise servers, and cloud instances) to balance latency, accuracy, and operational cost.

Key Responsibilities

● AI Agent Development: Design, build, and orchestrate autonomous single- and multi-agent systems capable of complex reasoning, planning, memory management, and external tool/API execution (using frameworks like LangGraph, CrewAI, AutoGen, LlamaIndex, or custom orchestrators).

● Hardware Sizing & Infrastructure Architecture: Evaluate, specify, and procure/provision hardware stacks for local, edge, or data-center AI workloads. Calculate exact GPU compute, VRAM bandwidth, CPU, RAM,storage IOPS, and thermal/power requirements for running open-weight LLMs, vision models, and embedding pipelines.

● Model Deployment & Serving Optimization: Deploy and serve open-source and proprietary models using high-throughput inference engines (vLLM, TensorRT-LLM, TGI, Triton Inference Server, Ollama). Apply quantization (AWQ, GPTQ, GGUF, FP8) to maximize throughput on target hardware.

● RAG & Enterprise Integration:



Build production-grade vector search pipelines (Milvus, Qdrant, pgvector) and securely connect AI agents to internal databases, ERPs, document management systems, and IoT/operational data streams.

● Software Stack & MLOps: Containerize and orchestrate AI services using Docker, Kubernetes, and NVIDIA Container Toolkit (CUDA/cuDNN stack management). Set up CI/CD pipelines for agent evaluation, observability (LangSmith, Arize Phoenix, Prometheus), and guardrails.

● Cost & Performance Benchmarking: Continuously benchmark token generation speeds, Time-To-FirstToken (TTFT), concurrency limits, and cost-per-1k-tokens between self-hosted hardware and commercial cloud APIs. Required

Qualifications & Skills

● Education: B.Tech/B.E. or M.Tech/M.S. in Computer Science, Artificial Intelligence, Data Science, or equivalent practical experience.

● Experience: 3–5+ years in Software/ML Engineering, with at least 1.5–2+ years specifically focused on LLMs, GenAI, and Agentic workflows in production.

● Agentic & LLM Stack: Advanced Python proficiency; deep familiarity with agent orchestration frameworks, function calling, Model Context Protocol (MCP), structured outputs, and vector databases.

● Infrastructure & Hardware Mastery: Deep understanding of GPU architectures (NVIDIA RTX Ada/Blackwell workstation cards, L40S, A100, H100), VRAM calculation for model weights + KV cache + context windows, multi-GPU tensor parallelism, and Linux server administration.

● Inference & Optimization: Hands-on experience with vLLM, TensorRT-LLM, ONNX Runtime, model quantization techniques, and fine-tuning (LoRA/QLoRA).

📌 AI Engineer (Agentic Systems, Deployment & Infrastructure Sizing) (Gurugram)
🏢 Antal International
📍 Gurugram