Senior AI Engineer, Agentic Systems

AI Technology Partners (AITP) is a leader in delivering cutting‑edge generative AI solutions and managed services, specializing in secure, customizable AI deployments for enterprises. Our offerings are designed to help organizations unlock the full value of AI while maintaining robust security and compliance across their infrastructures.

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  you like greenfield architecture, fast iteration, and measurable impact with enterprise clients, this is your playground.

• Design multi-agent architectures with robust state management, memory, and routing.
• Choose and implement leading frameworks such as Lang Graph/Lang Chain Agents, Microsoft Auto Gen, CrewAI, Llama Index 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.

• 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, Mongo
  
  DB Atlas, Pinecone, Weaviate, Milvus) and structured knowledge (SQL/Graph).
• Add deterministic fallbacks, circuit breakers, and caching to keep latency and cost predictable.

• Define SLIs/SLOs for agent runs; implement tracing, metrics, and logging (e.g., Langfuse + Open Telemetry) and build dashboards for run‑level analytics.
• Create evaluation harnesses (automatic + human‑in‑the‑loop) using tools such as Ragas, Deep Eval, 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.

• 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).

• 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.

• 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: Lang Graph/Lang Chain Agents, Auto Gen, CrewAI, Llama Index 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/Type Script, async patterns, APIs, testing, CI/CD, containerization.
• Clear communicator who can interface with clients and write crisp technical docs.

• Cross‑cloud exposure (AWS/GCP) and hybrid integrations; experience with enterprise connectors (SharePoint/One Drive, Service Now, Salesforce).
• Experience with structured output, constrained decoding, JSON Schemas, and program‑of‑thought planning.

Remote, US‑based candidates preferred. The role may involve working across multiple time zones.

• Ownership & velocity: Small team, big surface area. You’ll design, ship, and iterate quickly.
• Security by design: Data governance and safety are table stakes,…