Aitp
Senior AI Engineer, Agentic Systems
Remote (United States) · Senior
Sponsorship not specifiedDetected 23 days ago
TypeScriptPythonSQLMongoDBVector DatabasesAWSGCPAzureCI/CDPlatform EngineeringMachine LearningLLMsRAGAgentic AILLMOpsMLOpsLangGraphComplianceSalesforceHIPAASharePoint
About the role
- If you like greenfield architecture, fast iteration, and measurable impact with enterprise clients, this is your playground.
Responsibilities
- 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.
- Implement retrieval-augmented generation (RAG) patterns with vector stores (Azure AI Search, pgvector, MongoDB Atlas, Pinecone, Weaviate, Milvus) and structured knowledge (SQL/Graph).
- 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).
Requirements
- Must-have 5-8+ years in software/platform engineering with recent production LLM applications (not just prototypes).
Nice to have
- Azure-first experience (Azure OpenAI, Azure AI Studio, Azure Functions/Container Apps/AKS, Private Link/VNet, Key Vault, Entra ID).
- experience with enterprise connectors (SharePoint/OneDrive, ServiceNow, Salesforce).
- Experience with structured output, constrained decoding, JSON Schemas, and program-of-thought planning.
- The role may involve working across multiple time zones.
- How we work Ownership & velocity: Small team, big surface area.
- 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.
- Python/TypeScript, async patterns, APIs, testing, CI/CD, containerization.
Skills
- 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.
Benefits
- 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.
- Compensation We offer a competitive and flexible compensation package aligned to experience, scope, and engagement model.
- This may include base salary, performance incentives, and equity participation, designed to reward meaningful contributions and impact.
Company info
- What we offer Challenging work on meaningful, production agentic systems for enterprise clients.
Equal opportunity
- Statement AI Technology Partners is committed to equal employment opportunity in all practices and reaffirms that there shall be no unlawful discrimination against any employee or applicant for employment on the grounds of race, color, religion, sex, sexual orientation, gender identity, national origin, age, disability, or veteran status.
This listing is sourced directly from Aitp's careers page and normalized into a canonical job model.