> Markdown version of [/jobs/ext/4825592-ai-platform-engineer](https://www.wearedevelopers.com/jobs/ext/4825592-ai-platform-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # AI Platform Engineer - **Company:** SWIFT - **Location:** Dallas, TX, United States (Remote available) - **Experience:** Expert - **Contract:** Permanent contract - **Skills:** LangGraph Framework, Java (Programming Language), Artificial Intelligence, Cloud Computing, Continuous Integration, Elasticsearch, Python (Programming Language), Performance Tuning, OpenAI, Site Reliability Engineering Practices, Search Technologies, Pinecone, Model Garden (Google Cloud), QLoRA, LangChain, Large Language Models, Multi-Agent Systems, Hallucination Detection, Qwen, NeMo Guardrails, Llamaindex, Generative AI, Langfuse — LLM Observability and Analytics Platform, Agentic-AI, Rate Limiting, Usage Tracking, Pgvector, AI Platforms, LangSmith, Kubernetes, Low Latency, CrewAI, RAGAS (Retrieval Augmented Generation Assessment), Weaviate, AutoGen, Arize Phoenix, Ollama, LiteLLM, Machine Learning Operations, DeepEval, Model Context Protocol, Terraform, Promptfoo, Programming Languages - **Published:** November 21, 2026 - **Apply:** https://www.careerjet.com/jobad/us997ac1c1966187648c4357c45b991695 ## About the Role Typically 6+ years of software or platform engineering experience, with hands-on production ownership of AI or ML infrastructure. Must have personally built and operated agentic AI or LLM systems in production, not just prototypes. ## Description Build and operate a production-grade Agentic AI platform, including orchestration, model gateway, agent registry, retrieval, guardrails, evaluation, and observability. Responsible for platform reliability, security, performance, and cost optimization. Core Technical Skills * LLM & Agent Orchestration: LangGraph, LangChain, LlamaIndex, CrewAI, AutoGen, or Google Agent Development Kit (ADK); production multi-agent orchestration, state management, and retry/fallback design. * Model Serving & Gateway: LiteLLM, Portkey, Kong AI Gateway, TrueFoundry, or Vertex AI Model Garden; routing, fallback, rate limiting, and token/usage tracking. Open-weight model serving (Llama, Mistral, Gemma, Qwen) using vLLM, TGI, Ollama, or Vertex endpoints; fine-tuning and adapter techniques (LoRA/QLoRA). * Retrieval-Augmented Generation (RAG): Vector stores (Vertex Vector Search, Pinecone, Weaviate, pgvector, Elasticsearch), embedding models, chunking, hybrid and semantic search, reranking, and grounding-quality evaluation. * Agent Infrastructure: Model Context Protocol (MCP), tool/function-calling contracts, agent registries, permission enforcement, and separation of reasoning from acting agents. * Evaluation & LLMOps: RAGAS, DeepEval, Promptfoo, or OpenAI Evals; offline and online evaluation, regression suites, drift and hallucination detection; MLflow, LangSmith, Langfuse, Arize Phoenix, or Braintrust. * Guardrails & AI Security: NeMo Guardrails, Guardrails AI, Model Armor, or Lakera; prompt-injection, jailbreak, and data-leakage defense; PII detection and redaction. * Observability: OpenTelemetry-based tracing for LLM and agent calls, token, latency, and cost telemetry, and quality-signal monitoring. * Cloud & Runtime: Kubernetes, containers, GCP (GKE, Vertex AI, Cloud Run), Terraform, CI/CD, and SRE practices for production AI services. * Programming Languages: Strong Python; Go or Java is useful for platform services.