Lead Backend AI Engineer

Netweb Software; United States; Remote; USD 180,000 - 240,000; Full time

Job summary

NetWeb Software is hiring a Lead Backend AI Engineer to design and build scalable, secure, and production-ready Agentic AI platforms for enterprise IT and SecOps automation.

You will lead multi-agent AI initiatives, implement secure tool execution, and collaborate with SRE and security teams to ensure production readiness in a remote environment. The role requires 8+ years of experience and deep backend expertise.

Qualifications

• Golang and Python with concurrency, microservices, distributed systems.
• Experience with multi-agent AI systems using LangGraph, LangChain, Semantic Kernel, or LlamaIndex.
• Agent orchestration, state management, tool calling, durable workflows.
• LLM fine-tuning with LoRA/QLoRA and PEFT techniques.

Responsibilities

• Design and build scalable, secure, and production-ready AI platforms for enterprise IT and SecOps automation.
• Provide technical leadership and mentorship to the backend AI team and ensure reliable production deployment.

Skills

Golang

Python

Concurrency

Microservices

Distributed systems

AI systems design

Education

BE/ME in IT or Computer Engineering, MCA, MSc-IT, BCA or equivalent

Tools

LangGraph

LangChain

Semantic Kernel

LlamaIndex

custom agent frameworks

vLLM

Ollama

TensorRT-LLM

Job description

NetWeb Software is Hiring: Lead Backend AI Engineer Location: Remote Experience: 8+Years

We are looking for a Lead Backend AI Engineer to design and build scalable, secure, and production-ready Agentic AI platforms for enterprise IT and SecOps automation.

• Strong expertise in Golang and Python, including concurrency, asynchronous programming, microservices, and distributed systems.
• Hands-on experience building multi-agent AI systems using LangGraph, LangChain, Semantic Kernel, LlamaIndex, or custom agent frameworks.
• Experience with agent orchestration, state management, tool calling, durable workflows, and failure recovery.
• Practical experience in LLM fine-tuning (LoRA/QLoRA, DPO), Hugging Face PEFT/TRL, and open-weight models.
• Production experience with LLM inference and serving using vLLM, TensorRT-LLM, or Ollama, including model quantization.
• Strong understanding of RAG, GraphRAG, hybrid search, embeddings, reranking, vector databases (Qdrant, Milvus, pgvector), and graph databases (Neo4j/AWS Neptune).
• Experience implementing AI safety guardrails, sandboxed execution, dry-run validation, rollback mechanisms, and secure tool execution.
• Hands-on experience with automated AI evaluation using DeepEval, Ragas, or promptfoo, including CI/CD-integrated regression testing.
• Knowledge of enterprise infrastructure integrations, REST APIs, SSH/CLI automation, SNMP, gNMI, and OpenTelemetry.

Preferred Skills: OpenClaw, Browser-Use, NETCONF, gRPC, model distillation, and experience with Llama, Mistral, Qwen, or DeepSeek models.

Education: BE/ME in IT or Computer Engineering, MCA, MSc-IT, BCA, or equivalent qualification.

Candidates should demonstrate strong system design, technical leadership, problem-solving, communication, and the ability to build reliable AI systems for production environments.