Website:
fabconnect.co.in
Job details:
Key Responsibilities
- Agentic AI Development
- Design, build, and deploy production-grade AI agents using Azure AI Foundry,
- Copilot Studio, and multi-model orchestration frameworks.
- Architect multi-agent systems with clearly defined roles, handoffs, memory
- strategies, and tool-use patterns.
- Select models appropriate to each task — balancing capability, latency, cost, and
- compliance requirements.
- Integrate agents with enterprise systems via REST APIs, MCP servers,
- SharePoint, Dataverse, and D365.
- Apply sound architectural principles to agentic solutions, managing complexity
- and ensuring maintainability at scale.
- AI-Assisted Development
- Work within a spec-first, AI-assisted development methodology — producing
- the technical specification artefacts that enable AI tooling to generate
- reliable, reviewable output.
- Apply consistent engineering standards to AI-generated code: reviewing,
- refactoring, and taking full ownership of everything that ships.
- Remain current with the AI developer tooling landscape, understanding that the
- methodology and judgement matter more than any specific tool.
- Contribute to internal standards and practices for AI-assisted
- engineering.
Solution Delivery
- Own end-to-end technical delivery within the squad — from technical discovery
- through to production deployment and handover.
- Manage environment transitions, CI/CD pipelines, and Azure deployment
- processes.
- Deliver against sprint milestones with the accountability that client
- engagements require.
- Adapt technical approach efficiently when scope or direction shifts, maintaining
- delivery momentum and engineering quality.
- Raise technical concerns early with a considered alternative.
Client Engagement
- Present technical approaches and demonstrate working solutions to client
- stakeholders.
- Participate in client workshops, technical discovery sessions, and delivery
- governance reviews.
- Translate technical constraints into accessible language for non-technical
- audiences.
- Represent with professionalism and technical credibility across all client
- interactions.
Quality & Engineering
Standards
- Write clean, well-structured, documented code — maintaining this standard
- consistently regardless of delivery pressure or generation method.
- Embed responsible AI practices into every build: prompt injection defence, PII
- handling, content filtering, auditability, and security-by-design.
- Produce technical documentation, architectural decision records, and runbooks
- that support transition and ongoing operation.
- Conduct code reviews within the squad and contribute to broader
- engineering standards.
- Practice & Innovation
- Stay current with developments across AI engineering — models, frameworks,
- orchestration patterns, and tooling.
- Evaluate and share findings on emerging capabilities with practical application
- to client engagements.
- Contribute reusable components to AI IP library: agent templates,
- prompt libraries, integration patterns, and accelerator tooling.
Key Behavioural Competencies
Competency description
- Engineering at Scale
- Understands what becomes possible when deep software expertise meets AI-
- assisted development, and pursues that combination deliberately. Applies
- engineering knowledge to set the conditions for AI tooling to produce
- reliable output at pace — and reviews that output with the same rigour as
- hand-written code.
Software Craft
- Holds well-formed views on how code should be structured — clean interfaces,
- separation of concerns, testability, maintainability — and applies them
- consistently. Identifies structural problems before they compound,
- including in AI-generated output.
Principled Adaptability
- Knows when an engineering standard is non-negotiable and when a considered
- compromise is appropriate. Holds that position clearly when it matters,
- adjusts efficiently when circumstances warrant it, and can articulate the
- reasoning behind either.
- Technical Candour
- Raises structural or technical concerns early with a well-formed alternative.
- Engages constructively rather than deferring. When client direction
- changes, adapts the solution without losing sight of what makes it sound.
- Delivery Accountability
- Accountable for technical commitments. Finds the path that delivers against
- firm client deadlines without compromising engineering quality.
Curiosity & Learning
- Follows developments in the AI engineering landscape with genuine interest.
- Forms views on what is practically useful, shares those views with the team,
- and is straightforward about the limits of current knowledge.
- Professional
- Effectiveness
- Communicates technical ideas clearly to mixed audiences. Represents
credibly in client settings. Contributes positively to squad delivery and team
- environment.
- Dealing with Ambiguity
- Decides and acts without requiring a complete picture. Reprioritises promptly
- when circumstances change. Handles uncertainty and incomplete
- information without disruption to delivery.
Integrity & Trust
- Widely trusted. Presents the unvarnished truth in an appropriate and
- constructive manner. Admits mistakes and takes accountability for
- outcomes.
- Qualifications and Experience
- Skills
- Strong Python and / or TypeScript development capability.
- Hands-on experience with LLM APIs including prompt engineering, tool use,
- function calling, and structured outputs.
- Experience with agentic orchestration frameworks (Semantic Kernel, AutoGen,
- LangChain / LangGraph, or equivalent).
- Familiarity with RAG pipeline design, vector search, and enterprise data retrieval
- patterns.
- Azure platform proficiency: Azure AI Foundry, Azure OpenAI Service, AI Search,
- Functions, Container Apps, API Management.
- Familiarity with MCP (Model Context Protocol) or equivalent tool-integration
- approaches.
- Experience with AI-assisted, spec-driven development methodology.
- Knowledge of secure data handling, responsible AI practices, and compliance
- considerations in AI solution development.
- Proficiency with Git, CI/CD (Azure DevOps or GitHub Actions), and agile delivery
- practices.
- Experience
- 8+ years in a software development role, with at least 2 years delivering AI or
- agentic solutions in a commercial context.
- Demonstrated delivery of production-grade systems end-to-end in a client or
- enterprise environment.
- Experience working directly with clients or end-users as part of a delivery team.
- Experience integrating AI solutions with enterprise platforms (D365, SharePoint,
- Power Platform, or equivalent) desirable.
- Qualification
- Tertiary qualification in Computer Science, Software Engineering, or a related
- discipline preferred.
- Demonstrated equivalent experience will be considered.
- Microsoft certifications (AI-102, AZ-204, DP-203, or Power Platform equivalents)
- desirable.
Click on Apply to know more.