Flatworld Solutions is a leading IT and business services company delivering end-to-end technology solutions across software development, data management, AI/ML, and digital transformation. Our AI Solutioning team turns enterprise problems into working AI systems fast.

Role Summary :

We are hiring an Agentic AI Engineer to build AI agents that do real work inside enterprise processes - reading documents, calling systems, making bounded decisions, and handing off to people when they should. You will design and ship single-agent and multi-agent workflows that automate multi-step tasks across client systems such as CRMs, ERPs, ticketing platforms, email, and contact centres.

This role goes beyond chat. The hard part of agentic AI is reliability : agents that pick the right tool, recover from errors, stay within their permissions, and can be audited afterwards. You will work with the AI Solution Architect on design, the AI/ML Engineer on models and retrieval, and the Full Stack Engineer on the application layer. If you enjoy making autonomous systems dependable enough for a client to trust them with production work, this role will suit you.

Key Responsibilities :

Agent Design & Development :

- Design and build AI agents that plan and execute multi-step tasks using tool calling, structured outputs, and state management.

- Build multi-agent systems - orchestrator/worker, planner/executor, and review patterns - and decide when a single agent is the better choice.

- Translate business processes from BA and solution documents into agent workflows with clear goals, steps, decision points, and exit conditions.

- Design agent memory and context : conversation state, long-running task state, and retrieval of relevant knowledge at each step.

Tools, Integrations & MCP :

- Build and maintain the tools agents use - API connectors, database queries, document actions, and browser or desktop automation where no API exists.

- Develop Model Context Protocol (MCP) servers that expose client systems to agents in a secure, reusable way.

- Integrate agents with enterprise platforms such as Salesforce, ServiceNow, SAP, Microsoft 365, Google Workspace, and telephony systems.

- Write clear tool descriptions, input schemas, and error messages so agents use tools correctly and recover when a call fails.

Reliability, Safety & Evaluation :

- Build evaluation suites for agent behaviour : task success rate, tool-selection accuracy, step count, cost per task, and failure analysis on real traces.

- Design human-in-the-loop checkpoints for high-impact actions - approvals, escalations, and handoff to human agents.

- Enforce guardrails : least-privilege tool access, prompt injection defences, action limits, timeouts, and safe fallbacks.

- Instrument full traceability - log every model call, tool call, and decision so any agent run can be replayed and audited.

- Control cost and latency through model routing, caching, context management, and limits on runaway loops.

Deployment & Collaboration :

- Deploy agents as reliable services - containerised, observable, with queueing and retry handling for long-running tasks.

- Prepare demo-ready agent workflows for client pitches, working with the AI Solutions Lead on scenarios that show clear business value.

- Contribute reusable agent templates, tool libraries, and MCP connectors to Flatworld's AI accelerator library.

- Document agent architecture, tool inventories, permissions, and known limitations for every build.

Mandatory Technical Requirements :

- Python : Strong production-grade Python - clean, typed, tested code; async programming; API integration.

- LLM Tool Calling : Hands-on experience building applications with LLM tool/function calling and structured outputs on at least one major API (Anthropic, OpenAI, Google, or Azure OpenAI).

- Agent Frameworks : Built at least one working agent with LangGraph, CrewAI, AutoGen, OpenAI Agents SDK, Claude Agent SDK, or a well-structured custom orchestration loop.

- System Integration : Experience integrating with REST APIs, webhooks, and authentication schemes (OAuth, API keys, service accounts).

- Agent Evaluation & Tracing : Practice of testing agent behaviour with scenario-based test sets and inspecting execution traces - not just manual trial runs.

- Deployment : Ability to containerise with Docker and deploy services to a cloud platform; proficiency with Git.

Qualifications :

- Bachelor's or Master's degree in Computer Science, Information Technology, AI/ML, Engineering, or equivalent practical experience.

- 3 - 6 years of software engineering experience, including at least 1 - 2 years building LLM applications with tool use or agents.

- At least one agent or LLM automation taken from prototype to use with real users or real business data.

- Prior experience in an AI product company, an IT services AI practice, an automation/RPA team, or a startup is a plus.

What We Offer :

- Work at the front of applied AI - building agents that automate real enterprise processes, not just chat interfaces.

- Variety across industries and systems, with a direct line from your build to a client decision.

- Access to current commercial and open-weight models and freedom to choose the right framework for each problem.

- Mentorship from the AI Solutions Lead and AI Solution Architect, with exposure to pre-sales and solution design.

- Learning budget for AI upskilling, conferences, and cloud certifications.

- Competitive compensation with a clear path toward Senior Agentic AI Engineer or AI Solution Architect tracks.