Senior AI Engineer; AI-Native SDLC)

We are Fin Tech people. We enable financial institutions to become digital leaders.

As a global professional team, we work with best clients for great and exciting projects, in an environment where we learn amazing things every day. Each code, each voice, each contribution, each challenge, each success is celebrated here.

We welcome candidates who share our values, have the skills and are passionate to enjoy our journey to build the digital future of finance, together.

The Senior AI Engineer is a hands-on engineer responsible for designing, building, and scaling AI-driven solutions across the entire Software Development Life Cycle (SDLC), from requirements and design to coding, testing, and release, including LLM selection and cost optimization for these solutions.

The role is a builder of AI solutions, turning AI experiments into production-grade tools and agents that delivery teams use every day.

• Use AI to automate and optimize R&R-based SDLC process tasks, reducing manual effort while maintaining process compliance.
• Design and build LLM-based applications and agentic workflows across the SDLC, applying context engineering, agent orchestration, and MCP.
• Identify and prioritize AI and agentic use cases across the SDLC (requirements, design, development, testing, documentation, release) based on value, feasibility, and risk.
• Prototype quickly and take successful pilots to production-ready, reusable assets.
• Build RAG solutions over internal knowledge (product docs, SSDs, test assets).
• Build AI solutions to generate analysis artifacts and support AI Test Automation team for test case and test data generation, automation script generation, and self-healing.

• Integrate AI solutions with Jira, Confluence, Azure Dev Ops, and Git Hub via APIs and MCP.
• Define evaluation frameworks, guardrails, and monitoring (accuracy, hallucination, latency) and build reusable patterns for scaling AI solutions.
• Evaluate AI models, frameworks, and platforms for building SDLC solutions through hands-on PoCs.

• Benchmark and select LLMs per use case based on output quality, latency, and cost; apply model routing between large and smaller models.
• Analyse token consumption of AI solutions and agents, and track usage, budgets, and cost-per-task metrics.
• Optimize agent efficiency and cost through prompt and context optimization, prompt caching, RAG tuning, batching, and fewer unnecessary agent steps and tool calls.

• Pilot the AI solutions built on live projects; establish baselines and measure their impact on effort, quality, and usage.
• Document solutions and provide technical guidance and handover to the teams using them.

• Strong development and solid engineering practices for AI (clean code, testing, CI/CD).
• Hands‑on experience with AI coding assistants such as Claude Code or Git Hub Copilot.
• Experience with the Microsoft AI ecosystem (e.g., Copilot Studio, Azure AI Foundry) is a plus.
• Hands‑on experience with LLM APIs, agent frameworks, and MCP.
• Practical knowledge of RAG, embeddings, vector databases, prompt and context engineering, and LLM evaluation and monitoring.
• Understanding of test automation (e.g., Playwright) and requirement management.
• Experience integrating with Jira, Confluence, Azure Dev Ops, and Git Hub APIs and with cloud platforms; fluent in English.

• Bachelor's degree in Computer Science or related field;
  Master's in AI/ML is a plus.
• 7+ years of software engineering experience, including 2+ years of hands-on GenAI/LLM development.
• Proven experience applying AI to the SDLC (e.g., testing,…