LLM Engineer

Job Title:LLM Engineer
Location:Cincinnati, OH Remote
Duration: 6 months
Experience Required: 8-10

Job description:
All Fields are Mandatory


Yes US Citizen/GC US Citizen/GC


Education Start date (dd-mmm-yy) Duration of assignment (in Months)


Any degree 15-September-2026 1 Years


Remote USA 8+ Years

Must Have Technical/Functional Skills


The LLM Engineer will design, build, optimize, deploy, and operate Large Language Model and Small Language Model capabilities that power


the enterprise Agent Factory. This role is responsible for transforming foundation models into secure, reliable, reusable, and enterprise-


ready AI capabilities across agentic workflows, AI for SDLC, knowledge retrieval, model evaluation, private AI hosting, and AgentOps.


This engineer will work closely with the Principal AI Architect, AI Engineering Lead, Platform Engineers, Security, Enterprise Architecture,


Product Owners, and domain teams to build the intelligence layer of the Agent Factory. The role requires hands-on expertise in LLM


application development, RAG, prompt and context engineering, model evaluation, fine-tuning, model serving, and hosting LLMs or SLMs in cloud, hybrid, and on-prem environments. LLM and Generative AI • Large Language Models • Small Language Models • Prompt Engineering • Context Engineering • Retrieval-Augmented Generation • Embeddings • Semantic Search • Agentic AI Patterns • Multi-Agent Workflows • Tool Calling • Function Calling • Model Evaluation • LLM Observability Model Engineering • Fine-Tuning • Supervised Fine-Tuning • LoRA • QLoRA • Quantization • Distillation • Model Compression • Synthetic Data Generation • Model Benchmarking • Model Selection • Model Routing Model Hosting and Serving • Private LLM Hosting • On-Prem Model Deployment • GPU-Based Inference
• Model Serving APIs • High-Availability Inference • Autoscaling Patterns • Load Balancing • Caching • Batch and Real-Time Inference AI Infrastructure and Frameworks • Kubernetes • Docker • Kubeflow • KServe • Ray Serve • MLflow • Hugging Face • Transformers • PyTorch • PEFT • DeepSpeed • NVIDIA NIM • Triton Inference Server • TensorRT-LLM • vLLM • TGI • SGLang Programming and Engineering • Python • TypeScript or JavaScript • REST APIs • Microservices • CI/CD • GitHub or Azure DevOps • API Design • Distributed Systems
• Cloud-Native Engineering • Test Automation Data and Knowledge Systems • Vector Databases • Knowledge Graphs • Document Processing • Metadata Management • Data Pipelines • Object Storage • Enterprise Search • Structured and Unstructured Data Integration


Roles & Responsibilities


LLM Application Engineering
• Build enterprise-grade LLM-powered applications and intelligent agent capabilities.
• Design reusable LLM patterns, services, APIs, and accelerators for Agent Factory adoption.
• Develop model interaction patterns for reasoning, summarization, classification, extraction, planning, and decision support.
• Build reusable prompt, context, retrieval, memory, and evaluation components.
• Support AI for SDLC agents across requirements, design, coding, testing, security review, deployment, and operations.
• Collaborate with product and engineering teams to convert AI use cases into scalable production solutions.


Agent Factory Intelligence Layer
• Build the core intelligence services used by enterprise agents.
• Develop reusable capabilities for planning, task decomposition, reasoning, tool usage, and agent collaboration.
• Enable agent-to-agent interaction patterns and multi-agent orchestration support.
• Integrate LLM capabilities into agent runtimes, tool registries, workflow engines, and MCP-based gateways.
• Support human-in-the-loop, approval, escalation, and feedback workflows.
• Improve agent response quality, accuracy, safety, and task completion.


Prompt Engineering and Context Engineering
• Design and maintain reusable prompt engineering standards, templates, and libraries.
• Create system prompts, task prompts, role prompts, guardrail prompts, and evaluation prompts.
• Develop context engineering strategies to improve grounding, relevance, and personalization.
• Optimize token usage, context windows, memory injection, and retrieval inputs.
• Establish prompt versioning, testing, and governance practices. • Improve consistency of agent behavior across enterprise use cases. Retrieval-Augmented Generation • Design and implement enterprise RAG architectures. • Build retrieval pipelines using enterprise documents, knowledge repositories, structured data, and metadata. • Optimize chunking, embedding, indexing, ranking, reranking, and retrieval strategies. • Improve grounding, citation quality, precision, recall, and factual accuracy. • Build reusable retrieval services for multiple agents and business domains. • Partner with data, platform, and knowledge management teams to onboard trusted enterprise knowledge sources. LLM and SLM Model Engineering • Evaluate, build, fine-tune, deploy, and optimize LLMs and SLMs for enterprise use cases. • Support domain-specific model development using internal and approved datasets. • Build supervised fine-tuning and model adaptation pipelines. • Apply model optimization techniques such as LoRA, QLoRA, distillation, quantization, and model compression. • Evaluate commercial, open-source, and internally hosted models for suitability, quality, cost, and operational fit. • Support model selection strategies based on use case sensitivity, latency, accuracy, cost, and data residency requirements. Private AI and On-Prem Model Hosting • Build and support private AI capabilities for hosting SLMs and LLMs in enterprise-controlled environments. • Deploy models on on-prem, hybrid, and private cloud infrastructure. • Support GPU-enabled model hosting using enterprise AI infrastructure. • Optimize model serving for latency, throughput, concurrency, resiliency, and GPU utilization. • Build secure inference endpoints for internal agent and application consumption. • Support air-gapped or restricted AI environments where required by security or compliance needs. • Partner with infrastructure and platform teams to operationalize private model hosting patterns. Model Serving and Inference Optimization • Implement scalable model serving using modern inference frameworks. • Build high-availability inference patterns for production workloads. • Optimize inference performance, token throughput, response latency, and cost efficiency. • Implement model routing, load balancing, caching, and fallback strategies. • Support batch inference and real-time inference use cases. • Develop reusable deployment templates for multiple model families and serving patterns. LLMOps, ModelOps, and AgentOps
• Build operational practices for managing models and agents across the lifecycle. • Implement observability for prompts, retrieval, model responses, latency, cost, and failures. • Develop evaluation pipelines for regression testing and continuous quality improvement. • Monitor model drift, response quality, hallucination indicators, and safety risks. • Support CI/CD and release management for prompts, models, agents, and retrieval pipelines. • Build dashboards and metrics for AI quality, reliability, adoption, and operational readiness. AI Evaluation and Benchmarking • Define and implement LLM evaluation frameworks. • Measure accuracy, groundedness, relevance, hallucination rate, toxicity risk, safety compliance, task completion, and user satisfaction. • Build automated test suites for prompts, agents, tools, and RAG pipelines. • Benchmark models across enterprise use cases. • Compare cloud-hosted, open-source, and on-prem models based on performance, cost, quality, and risk. • Support go/no-go quality gates for production AI releases. Responsible AI, Security, and Governance • Embed Responsible AI controls into LLM applications and agent workflows. • Implement guardrails for safe output, tool usage, data access, and enterprise policy compliance. • Support model risk management, auditability, transparency, and traceability. • Ensure sensitive data is handled according to enterprise security and privacy requirements. • Partner with Security, Enterprise Architecture, Risk, and Compliance teams. • Support governance workflows for model approval, agent approval, and production readiness.

Generic Managerial Skills, If any


LLM and Generative AI
• Large Language Models
• Small Language Models
• Prompt Engineering
• Context Engineering
• Retrieval-Augmented Generation
• Embeddings
• Semantic Search
• Agentic AI Patterns
• Multi-Agent Workflows • Tool Calling • Function Calling • Model Evaluation • LLM Observability Model Engineering • Fine-Tuning • Supervised Fine-Tuning • LoRA • QLoRA • Quantization • Distillation • Model Compression • Synthetic Data Generation • Model Benchmarking • Model Selection • Model Routing Model Hosting and Serving • Private LLM Hosting • On-Prem Model Deployment • GPU-Based Inference • Model Serving APIs • High-Availability Inference • Autoscaling Patterns • Load Balancing • Caching • Batch and Real-Time Inference AI Infrastructure and Frameworks • Kubernetes • Docker • Kubeflow • KServe • Ray Serve
• MLflow • Hugging Face • Transformers • PyTorch • PEFT • DeepSpeed • NVIDIA NIM • Triton Inference Server • TensorRT-LLM • vLLM • TGI • SGLang Programming and Engineering • Python • TypeScript or JavaScript • REST APIs • Microservices • CI/CD • GitHub or Azure DevOps • API Design • Distributed Systems • Cloud-Native Engineering • Test Automation Data and Knowledge Systems • Vector Databases • Knowledge Graphs • Document Processing • Metadata Management • Data Pipelines • Object Storage • Enterprise Search • Structured and Unstructured Data Integration
• Experience deploying open-source models such as Llama, Mistral, Mixtral, Phi, Gemma, Qwen, DeepSeek, Granite, Falcon, or domain-specific models. • Experience hosting models on GPU infrastructure such as NVIDIA H100, H200, B200, B300, A100, L40S, GH200, or AMD MI300X. • Experience with private AI, hybrid AI, or air-gapped AI environments. • Experience with healthcare, financial services, insurance, or other regulated industries. • Experience building enterprise copilots, AI assistants, or agent platforms. • Experience with MCP, tool registries, agent runtimes, or enterprise integration patterns. • Experience with Responsible AI, model governance, model risk management, and AI compliance practices. • Experience optimizing AI workloads for cost, performance, latency, and security.


Role Descriptions: LLM
Essential Skills: LLM
Desirable Skills:
Keyword:
Skills: AI and Automation