Senior AI Engineer, Agentic Systems

Senior AI Engineer, Agentic Systems Employment type: Full-Time (Permanent) or Contract (40 hrs/week) Location: Remote (U.S. preferred). Why AITP / Why this role At AI Technology Partners (AITP), we empower enterprises to scale revenue & profit —with secure, compliant generative AI solutions. In this role, you’ll lead the design and delivery of agentic systems that orchestrate tools, data, and policies to solve real business workflows—safely, reliably, and at scale. If you like greenfield architecture, fast iteration, and measurable impact with enterprise clients, this is your playground. What you’ll do Architecture & System Design (Agentic) · Design multi-agent architectures with robust state management, memory, and routing. · Choose and implement leading frameworks such as LangGraph/LangChain Agents, Microsoft AutoGen, CrewAI, LlamaIndex Agents, Semantic Kernel, or Haystack Agents—and justify trade-offs. · Build modular components (planners, tool registries, policy guards, evaluators) that are reusable across clients and domains. Tooling & Orchestration · Integrate enterprise tools and data sources via function/tool calling, webhooks, and event-driven flows (Queues/Service Bus/Functions). · Implement retrieval-augmented generation (RAG) patterns with vector stores (Azure AI Search, pgvector, MongoDB Atlas, Pinecone, Weaviate, Milvus) and structured knowledge (SQL/Graph). · Add deterministic fallbacks, circuit breakers, and caching to keep latency and cost predictable. Reliability, Observability & MLOps · Define SLIs/SLOs for agent runs; implement tracing, metrics, and logging (e.g., Langfuse + OpenTelemetry) and build dashboards for run-level analytics. · Create evaluation harnesses (automatic + human-in-the-loop) using tools such as Ragas, DeepEval, promptfoo to measure groundedness, task success, safety, and cost. · Productionize with CI/CD, environment promotion, feature flags, and canary strategies; optimize cost-per-task and time-to-success. Safety, Security & Governance · Enforce content and safety policies (redaction, classification, guardrails) with policy-as-code; implement role/tenant isolation and data minimization. · Collaborate with security teams to align to ISO 27001/SOC 2/NIST/HIPAA/GDPR contexts; deliver audit-ready evidence for agentic workflows. · Build privacy-first patterns (no data exfiltration by default, least-privilege tool access, secure prompt/trace storage). Product & Client Impact · Work directly with enterprise client teams to translate business processes into agentic designs; present trade-offs and proofs-of-value that lead to production. · Partner with solution leads to create domain-specific agents (e.g., RFP assist, incident RCA drafting, knowledge ops) and reusable templates. Requirements Must-have · 5–8+ years in software/platform engineering with recent production LLM applications (not just prototypes). · Hands-on expertise with agentic frameworks (one or more of: LangGraph/LangChain Agents, AutoGen, CrewAI, LlamaIndex Agents, Semantic Kernel, Haystack Agents) and tool/function-calling patterns. · Strong RAG engineering across vector DBs, chunking/embedding strategies, metadata/search ranking, and grounding techniques. · Proven track record building observable, cost-aware, and secure LLM systems (tracing, evals, guardrails, secrets/IAM, PII handling). · Solid software engineering fundamentals: Python/TypeScript, async patterns, APIs, testing, CI/CD, containerization. · Clear communicator who can interface with clients and write crisp technical docs. Nice to have · Azure-first experience (Azure OpenAI, Azure AI Studio, Azure Functions/Container Apps/AKS, Private Link/VNet, Key Vault, Entra ID). · Cross-cloud exposure (AWS/GCP) and hybrid integrations; experience with enterprise connectors (SharePoint/OneDrive, ServiceNow, Salesforce). · Experience with structured output, constrained decoding, JSON Schemas, and program-of-thought planning. Benefits How we work · Ownership & velocity: Small team, big surface area. You’ll design, ship, and iterate quickly. · Security by design: Data governance and safety are table stakes, not afterthoughts. · Evidence over vibes: We measure task success, grounding, and cost—and improve with data. · AI as leverage: We use LLMs to accelerate engineering—not replace it. Compensation · Competitive salary or hourly rate, commensurate with experience and engagement model. What we offer · Challenging work on meaningful, production agentic systems for enterprise clients. · Learning & sharing culture with deep dives, brown bags, and support for certifications/publication. · Inclusive, flexible workplace—bring your whole self; work where you do your best thinking. Apply Send your resume and a brief note (or links) highlighting a production LLM/agentic system you built: what it did, how you measured success, and what you’d improve next. AI Technology Partners is an equal opportunity employer. We do not discriminate based on race, color, religion, sex, sexual orientation, gender identity, national origin, age, disability, or veteran status.