Job Title: Contractor -AI Engineer Schedule- M-F 9-5PM
Location: memphis TN
Contract Length: 6-12 months
LLM Platform Engineer for GenAI Infrastructure Overview is seeking a highly skilled engineer with deep expertise in large language models (LLMs), information retrieval, and distributed systems to design and build the foundation for GenAI applications at
enterprise scale. This role is not about building end-user AI appsit is about creating the centralized AI infrastructure that will enable 50+ teams across the organization to innovate securely, efficiently, and consistently. The contractor will lead the design
and implementation of an enterprise LLM Gateway, a central API layer that mediates all LLM interactions, enforcing governance, security, observability, and performance best practices. Over time, you will extend this platform with retrieval-augmented generation
(RAG) capabilities and shared vector database integrations.
ESSENTIAL JOB FUNCTIONS
LLM Gateway Design & Development
Architect and implement an enterprise-grade LLM Gateway serving as the single-entry point for all application teams.
Build mediation pipelines for prompt cleansing, PII detection/masking, guardrails, linting, throttling, and quota enforcement.
Ensure system supports multi-tenant, policy-driven routing and governance. Governance, Security, and Observability
Design centralized controls to enforce organizational compliance and security policies across all LLM usage.
Enable logging, monitoring, and reporting for auditability, cost tracking, and usage insights.
Implement safeguards to mitigate brand and messaging risks, ensuring LLM outputs remain aligned with enterprise communication standards, especially in consumer-facing applications.
Future RAG & Vector Database Integration
Architect a shared, hybrid retrieval-augmented generation layer to support enterprisewide use cases.
Design abstraction layers to minimize coupling with any one vector database provider, enabling portability and cost optimization.
Optimize information retrieval pipelines: semantic search, embeddings, metadata filtering, hybrid retrieval.
Research & Systems Thinking: Apply formal methods, distributed systems design, and computer science principles to ensure correctness, scalability, and resilience.
Stay current with advancements in embeddings, search algorithms, vector stores, and LLM serving platforms.
Advise teams on tradeoffs of embedding models, vector DB choices, and migration strategies.
REQUIREMENTS
Strong background in Computer Science, Machine Learning, or related field (M.S. preferred).
Deep expertise in LLM integration, prompt/response mediation, and GenAI system design. Hands-on experience with vector databases (e.g., Pinecone, Weaviate, Milvus, FAISS, Vespa, pgvector) and embedding models.
Knowledge of information retrieval methods: dense retrieval, semantic search, filtering, hybrid approaches.
Experience building distributed, high-scale backend systems with strong governance/security requirements.
Hands-on experience with cloud-native development such as AWS, including containerization technologies (e.g., Docker, Kubernetes) and CI/CD pipelines for scalable deployment and automation.
Proficiency in at least one modern programming language used in AI/ML systems (Python, Java, Go, etc.).
Familiarity with frameworks such as LangChain, LlamaIndex, LiteLLM, or equivalent orchestration layers.
Familiarity with Microsoft M365 Copilot (strongly preferred) and Salesforce Agentforce (nice to have), particularly in the context of LLM integration and governance.
Strong systems thinking: ability to design abstractions, modularity, and portability across providers.
Excellent communication skillsable to collaborate with both technical and nontechnical stakeholder.
SKILLS PREFERRED
Experience with policy-driven API gateways or enterprise middleware. Knowledge of formal verification methods or program analysis techniques for correctness/guardrails.
Prior work on multi-tenant ML platforms or enterprise ML Ops Contributions to open-source libraries in LLM/RAG/vector search space.
Impact: This role is foundational. The infrastructure you build will enable several internal teams to safely and effectively leverage GenAI, while ensuring the enterprise maintains control, compliance, and efficiency
Contact Information
Email: dinesh@confiminds.com
Click the email address to contact the job poster directly.