Role Description We are looking for AI Engineering Tech Lead to drive the design and delivery of AI agent systems and multi-agent architectures. This is a technical leadership role combining deep hands-on engineering with technical leadership — guiding architectural decisions, mentoring engineers, and maintaining high standards across the codebase. Qualifications - 5+ years of experience in software engineering with a strong focus on AI/ML systems - Expert-level Python skills, including async programming and design patterns - Demonstrated experience building AI agents and multi-agent systems using LangChain and LangGraph - Strong practical knowledge of LLM integration patterns: prompt engineering, function/tool calling, retrieval-augmented generation (RAG), embeddings, and vector search - Extensive experience with cloud platforms - AWS and/or Azure - including deployment, scaling, and management of AI workloads - Solid general ML foundation: understanding of model training, evaluation, inference pipelines, and the broader ML development lifecycle - Strong CI/CD pipeline expertise - Hands-on experience with containerization and orchestration in production environments - Practical experience with infrastructure-as-code tools for managing cloud resources reliably and repeatably - Experience implementing AI observability - Proficiency in using AI tools for everyday tasks (Claude Code, Cursor, Advanced prompting, etc.) - Experience designing and building robust APIs (FastAPI, Flask, or similar) and integrating them into larger system architectures - Proficiency with SQL and NoSQL databases - Ability to lead technical discussions, conduct meaningful code reviews, and mentor team members - Upper-Intermediate English or higher Requirements - High knowledge of core ML frameworks (would be an advantage) - Hands-on experience with AWS SageMaker and broader AWS ML ecosystem (would be an advantage) - Solid understanding of the full ML lifecycle (would be an advantage) Responsibilities - Lead the technical design and architecture of AI agent platforms and multi-agent workflows built on LangChain and LangGraph - Hands-on development of AI agents - Integrate LLMs from providers such as OpenAI, Anthropic, and Azure OpenAI into production-grade agent pipelines - Build and optimize CI/CD, containerization, and infrastructure-as-code practices for the team - Establish and maintain AI observability across agent systems - tracing execution paths, monitoring performance, tracking costs, and surfacing anomalies - Mentor and guide engineers through code reviews, architectural discussions, and knowledge sharing sessions - Collaborate with product managers, solution architects, and stakeholders to align technical implementation with business objectives - Ensure system reliability, scalability, and maintainability through clean architecture, automated testing, and deployment best practices - Contribute to defining engineering standards, development workflows, and documentation practices across the team - Contribute to technical solutions for AI-oriented proposals during pre-sale cycles

• You’ll build and maintain reliable automation that interacts with real-world web portals and third-party systems—where correctness, traceability, and security matter as much as speed. • Own the design, development, and operation of web-portal automation workflows using Playwright (and related tooling). • Build automation services primarily in Python, with strong supporting development in TypeScript. • Implement evaluation/validation (“evals”) to measure automation accuracy, catch regressions, and improve reliability over time. • Maintain strong audit-trail discipline: deterministic logging, event traces, artifacts, and reproducible runs for debugging and compliance needs. • Design automation with a security-first mindset, following best practices for handling sensitive workflows and data. • Collaborate with engineering/product stakeholders to translate ambiguous real-world processes into pragmatic, shippable automation. • Improve robustness against common automation challenges (dynamic UIs, flaky states, rate limits, auth flows, partial failures) while keeping systems maintainable.

• Set architectural direction for products emerging from Labs, from prototype to production • Design and build production-grade agentic workflows: retrieval, tool use, multi-step planning, human-in-the-loop checkpoints, and safety guardrails • Be the senior technical voice in architectural decisions that span multiple teams • Establish technical standards and engineering practices that extend across the organization • Make significant individual contributions to the SaaS product across Azure and AWS • Collaborate with product, design, and engineering across the full SDLC • Mentor and guide engineers and actively influence engineering culture • Ensure performance, quality, and responsiveness of customer-facing applications and the agentic systems built on top of them • Implement and maintain modern automated testing practices, including evals for AI components • Contribute to modernization and consolidation of legacy surfaces as integration touch points emerge

• Co-create solutions with business and technical stakeholders through workshops, rapid iterations, and hands-on delivery. • Locate, qualify, and secure access to the data required for each use case, working directly with the Data Engineer. • Translate use cases into production-ready GenAI and agentic AI solutions, including RAG architectures, intelligent assistants, and AI-enabled workflows. • Prototype, test, deploy, monitor, and improve solutions in real client environments using feedback from users and domain experts. • Work with Data Engineers, Software Engineers, Foundations Architects, Governance experts, Business Value Advisors, and Service Delivery Managers to deliver sustainable outcomes. • Balance speed, quality, cost, security, and maintainability while making clear technical and delivery trade-offs. • Define success criteria from the outset, including adoption, performance, reliability, risk, cost, and measurable business value. • Ensure solutions are documented, governed, and transferable so clients can operate them with confidence. • Turn successful delivery into reusable patterns, accelerators, and building blocks that strengthen future engagements.