Artificial Intelligence Senior Associate (W2 Position)

We are looking for a Senior AI / LLM Engineer to architect and deploy production-grade multi-agent orchestration layers, advanced RAG pipelines, and automated intelligence workflows. This role is closer to distributed systems engineering with a probabilistic component than basic prompt tuning or pure ML research. You will translate complex business requirements into scalable, observable, and secure AI systems on Google Cloud Platform (GCP), working with frameworks like LangGraph, CrewAI, and LlamaIndex, and containerized backend microservices. Key Responsibilities Architect & Deploy Multi-Agent Orchestration: Build production-grade multi-agent architectures (orchestrator, NL-to-SQL, visualization, RCA/RAG, report generation, notification agents) using stateful agent frameworks with checkpointing and human-in-the-loop validation. Production RAG Systems: Design and scale Retrieval-Augmented Generation (RAG) pipelines using vector databases (pgvector, Pinecone, Weaviate, Qdrant), hybrid search, reranking, and domain-specific chunking strategies. GCP Infrastructure & Integration: Deploy agent microservices and data pipelines using GCP infrastructure (Vertex AI, Cloud Run / GKE, BigQuery, Pub/Sub, CI/CD with Docker/Kubernetes). LLM Observability & Testing: Build robust evaluation and tracing pipelines using tools like LangSmith, Langfuse, or OpenTelemetry ( golden datasets, LLM-as-judge scoring, latency/cost tracking). Safety & Guardrails: Implement prompt-injection defense, output validation, safe execution of AI-generated code/SQL (least-privilege access, sandboxing), and human approval checkpoints for critical actions. Cost & Latency Optimization: Implement tiered model routing (low-cost filtering models vs. high-capability deep-dive models) and intelligent caching strategies. Integration & Collaboration: Connect validated outputs to enterprise operational platforms (e.g., Salesforce, notification systems, reporting tools) and collaborate with data scientists to turn prototypes into production-ready services. Qualifications & Skill Requirements Required Experience & Education

Education: Bachelor’s degree in Computer Science, Software Engineering, or a related technical field (Master’s preferred). Experience: 3+ years in production software engineering, including 1 2+ years actively building ML/AI or LLM-driven applications in production environments. Cloud Expertise: Hands-on experience with Google Cloud Platform (GCP) (BigQuery, Vertex AI, Cloud Run, GKE, Pub/Sub). Language & Backend: Strong proficiency in Python (async/concurrent programming) and backend frameworks (FastAPI, Flask). Agent Orchestration: Practical experience using frameworks like LangGraph, CrewAI, LlamaIndex, or equivalent for multi-step agent workflows. Vector DBs & RAG: Hands-on experience with vector search and databases (pgvector, Pinecone, Qdrant, Weaviate). DevOps & Data: Proficiency with Docker, Kubernetes, CI/CD pipelines, and writing complex SQL queries. LLM Security & Observability: Familiarity with LLM guardrails, sandboxing, and evaluation tooling (LangSmith, Langfuse, OpenTelemetry). Preferred Qualifications (Nice-to-Have): Experience designing model-routing pipelines for cost optimization at scale. Hands-on experience with human-in-the-loop or high-stakes validation checkpoints. Industry experience with automotive, EV charging, IoT, or connected-vehicle telemetry data. Familiarity with the Model Context Protocol (MCP) or open integration standards across tools/agents. Prior experience in 0-to-1 product environments or startups handling fast-evolving requirements., Akkodis is seeking a Senior Artificial Intelligence Associate for a Contract with a client in Dearborn, MI (Hybrid). The ideal candidate with proven experience designing and deploy…

• 10 hours ago

• $95,000-140,000 per year