Senior AI/ML Engineer

We're looking for a Senior AI/ML Engineer to guide the design, architecture, and production rollout of agentic AI systems — autonomous and semi-autonomous agents, multi-agent workflows, copilots, and tool-using LLM applications. This is an advisory role: you'll set technical direction, review architectures, mentor junior engineers, and build reference implementations while staying close enough to implementation to make grounded technical decisions. What You'll Advise On & Build Agentic Architecture & Orchestration Design agent architectures and orchestration strategies with explainability. Architect multi-agent workflows and coordination patterns Define autonomy levels, guardrails, and human oversight mechanisms Build scalable workflows for long-running agent processes Agent Reasoning, Reliability & Evaluation Design tool-use, memory, and reasoning systems Improve reliability through validation, fallbacks, and recovery mechanisms Establish evaluation frameworks and quality benchmarks Implement observability, monitoring, and performance tracking Retrieval & Knowledge Systems Design retrieval pipelines that improve agent grounding and accuracy, including graph- and tree-based methods. Guide indexing, retrieval, reranking, and knowledge architecture decisions Evaluate retrieval quality and its impact on system performance Model & Platform Guidance Advise on model selection, deployment, and optimization strategies, including evaluating the trade-offs between managed API services and self-hosted models to prioritize client data security, cost efficiency, and performance. Balance quality, latency, reliability, and cost considerations by architecting production environments that meet strict service-level agreements (SLAs) while ensuring operational expenses remain optimized. The Advisory Dimension You'll: Set architecture and engineering standards Review designs and act as a technical escalation point Mentor engineers on agentic AI best practices Translate business requirements into scalable technical solutions Build prototypes and reference implementations that others can extend Core Requirements 4+ years of professional software, ML, or AI engineering experience Demonstrable experience building and deploying production-grade agentic systems Strong understanding of agent orchestration, tool use, memory, and evaluation Experience with RAG systems and retrieval fundamentals Strong backend engineering skills and production mindset Excellent communication and technical leadership abilities Expected Experience With Python OpenAI, Anthropic, Gemini, or similar LLM APIs LangGraph, CrewAI, AutoGen, or equivalent frameworks Pinecone, Weaviate, Qdrant, FAISS, Neo4j, or similar vector databases LangSmith, Langfuse, or comparable tooling Nice to Have Experience designing multi-agent systems from the ground up Familiarity with AI safety, guardrails, and governance Experience building internal AI platforms or reusable infrastructure Strong product mindset and user-centric thinking Experience with LLMOps and MLOps practices Proficiency in MELT (Metrics, Events, Logs, Traces) for monitoring AI systems Familiarity with other relevant AI deployment and maintenance tools