Agentic Engineer

Role Summary

We are looking for an Agentic Engineer to design, build, and deploy enterprise‑grade autonomous and semi‑autonomous AI agents that power high‑impact decision workflows. This is a systems engineering role focused on moving solutions from proofs of concept (PoCs) to reliable, governed, production‑ready agentic systems operating at scale.

You will work across planning–execution–verification loops, tool‑using agents, multi‑agent coordination, and observability, tightly integrated with enterprise data, applications, and security controls.

Key Responsibilities

• Design and implement agentic workflows (single‑agent and multi‑agent) for complex business decision‑making and task automation
• Build agents capable of planning, reasoning, acting, verifying outcomes, and recovering from failures using tools, memory, and contextual graphs
• Integrate large language models (e.g., GPT‑4 / GPT‑4o or equivalent) with enterprise systems via APIs and event‑driven architectures
• Develop orchestration layers using frameworks such as LangChain, Semantic Kernel, or custom agent runtimes
• Implement robust guardrails, including error handling, retries, fallback logic, and deterministic controls around probabilistic systems
• Instrument observability and evaluation mechanisms to measure task success, reliability, latency, and safety
• Collaborate with product teams, domain SMEs, and data teams to translate business logic into executable agent behaviors
• Ensure security, access control, compliance, and auditability across all agent actions and decision flows

Requirements

• Strong hands‑on experience building LLM‑based or agentic systems, including tool use, memory, routing, and planning
• Proficiency in Python and modern backend engineering practices
• Deep understanding of prompt engineering, embeddings, context management, and reasoning patterns
• Experience with orchestration and evaluation frameworks such as LangChain Agents, LangSmith, TruLens, or RAGAS
• Strong experience with API integration and data transformation across enterprise systems
• A production‑oriented mindset with emphasis on logging, monitoring, reliability, and failure handling

Good to Have

• Experience with multi‑agent architectures, including agent‑to‑agent communication and control planes
• Familiarity with the Azure AI ecosystem and cloud‑native deployment patterns
• Experience in regulated or high‑stakes domains such as finance, healthcare, pricing, or RGM
• Exposure to optimization or fine‑tuning techniques (e.g., LoRA, QLoRA, evaluation‑driven iteration)

Education

• Bachelor's degree in Computer Science, Information Technology, or a related field (mandatory)

Experience

• 4+ years of overall professional experience, including a minimum of 2+ years of relevant hands‑on experience building agentic systems using agent frameworks, LLMs, and LangChain