AI Systems & Deployment Engineer
Full-Time • Engineering• AI/ML Infrastructure
ROLE OVERVIEW
We are looking for an AI Systems & Deployment Engineer to own the full lifecycle of large language model deployments — from initial model selection and fine-tuning through production scaling and continuous optimization. You will work at the intersection of cutting-edge ML research and enterprise infrastructure, turning state-of-the-art models into reliable, low-latency services that power real products.
KEY RESPONSIBILITIES
Deploy and scale open-source and proprietary LLMs using up-to-date inference engines; establish and maintain CI/CD pipelines for ML models in production.
Fine-tune and optimize models for low-latency inference, including quantization, distillation, and throughput benchmarking.
Architect advanced Retrieval-Augmented Generation (RAG) pipelines and integrate enterprise vector databases (e.g., Pinecone, Weaviate, pgvector).
Design and build multi-agent systems — orchestrating tool use, memory, and inter-agent communication for complex autonomous workflows.




Partner directly with Infrastructure Engineers to ensure GPU cluster efficiency, cost optimization, and uptime SLAs.
Utilize the NVIDIA software stack (CUDA, TensorRT, Triton Inference Server) to maximize hardware efficiency and throughput.
REQUIRED QUALIFICATIONS
3+ years in AI/ML software engineering, with at least 1 year focused on production LLM deployments, fine-tuning, and RAG architectures.
Hands-on experience with inference frameworks such as vLLM, TGI, TensorRT-LLM, or ONNX Runtime.
Proficiency in Python and familiarity with MLOps tooling (MLflow, Weights & Biases, DVC, or similar).
Strong understanding of transformer architectures and common fine-tuning techniques (LoRA, QLoRA, RLHF).
Experience deploying containerized ML workloads on Kubernetes or equivalent orchestration platforms.
Ability to evaluate and benchmark models across latency, throughput, and quality dimensions.
PREFERRED QUALIFICATIONS
E

📌 AI Systems (India)
🏢 EnterOne
📍 India