What are the responsibilities and job description for the AI Foundation Model Engineer (LLM / Agentic AI / Full-Stack AI Engineering) position at Niche IT Software Solutions LLC?
AI Foundation Model Engineer
LLM / Agentic AI / Full-Stack AI Engineering
Level: Senior Individual Contributor
Experience: 9 years
Role Overview
We are seeking a Senior AI Foundation Model Engineer to build and deploy secure, scalable, enterprise-grade AI solutions using LLMs, RAG and agentic workflows. The role involves developing production AI applications and reusable services for an AWS-hosted, cloud-agnostic AI platform.
Key Responsibilities
· Build LLM applications, RAG pipelines, knowledge assistants, document intelligence solutions and workflow agents.
· Develop embeddings, semantic search, reranking, grounding and citation capabilities.
· Deploy and manage AI services using APIs, Docker, Kubernetes, CI/CD and cloud-native infrastructure.
· Collaborate on Terraform/IaC, environment promotion, release controls and rollback procedures.
· Optimize models and inference for accuracy, latency, throughput, token usage, reliability and cost.
· Implement LLMOps/MLOps covering evaluation, monitoring, observability, feedback loops and continuous improvement.
· Ensure security, privacy, Responsible AI, governance and audit readiness.
· Maintain production documentation, runbooks and release records.
Required Skills
· Strong hands-on experience with LLMs, transformers, GenAI, RAG, embeddings and vector databases.
· Advanced Python skills and experience with PyTorch, TensorFlow, Hugging Face, LangChain, LlamaIndex, Semantic Kernel or similar frameworks.
· Production deployment experience using APIs, containers, Kubernetes, CI/CD and monitoring tools.
· Practical AWS AI/cloud experience, preferably with Bedrock, SageMaker, OpenSearch, Lambda and EKS/ECS.
· Working knowledge of Terraform/IaC, MLOps/LLMOps, model evaluation, inference optimization and secure data handling.
Preferred Experience
· Banking, risk, compliance, financial crime or enterprise technology experience.
· Experience with Kendra, Azure OpenAI, Vertex AI, Databricks, vLLM, Triton, MLflow, Kubeflow or model gateways.
· Knowledge of LoRA, PEFT, instruction tuning, quantization, model governance and private/open-source LLM deployments.
Alternate Titles: LLM Engineer, GenAI Engineer, AI Platform Engineer, RAG Engineer, Applied ML Engineer or NLP Engineer.