• Designing and implementing AI agents with reasoning pipelines (e.g., multi-step workflows, RAG-based decision making) • Integrating AI capabilities such as LLM-powered services, semantic search, and intelligent automation • Contributing to scalable architectures for data- and event-driven systems • Improving, refactoring, and maintaining existing code bases • Designing tasks in collaboration with the Team Lead and Product Owner • Participating in code reviews, architecture discussions, and knowledge sharing

• Design, build, and deploy production AI applications, copilots, retrieval systems, and agentic workflows • Translate business problems into scalable technical solutions using modern AI engineering best practices • Develop backend services, APIs, and application architectures that integrate AI capabilities into enterprise systems • Build multi-agent systems, AI agents, workflow automation, and decision-support systems • Deploy AI solutions into production with appropriate security, observability, monitoring, evaluation, and governance • Design AI systems that integrate with enterprise data platforms, APIs, databases, messaging systems, and business applications • Collaborate with cross-functional client teams including engineering, data, product, architecture, security, and business stakeholders • Experience deploying and operating containerized applications on Kubernetes, including scaling, service networking, resource management, and production monitoring • Contribute reusable accelerators, frameworks, technical assets, and thought leadership that strengthen the AI Engineering practice • Stay current with emerging AI technologies and recommend practical approaches that improve client outcomes

• Lead end-to-end architecture for data platforms and pipelines: scraping, data extraction, transformation, storage, serving, and ML/LLM integration, balancing performance, reliability, security, and cost. • Incrementally scale pipelines and systems: design safe rollout plans and north star data-quality metrics to handle customer and traffic growth without impacting production. • Translate business goals into actionable data products: assess high-level requirements, carve clear problem spaces, draft crisp RFCs, and sequence work into deliverable projects for the team. • Establish and enforce engineering standards: testing strategy, evals, observability, data contracts, and security practices across services. Think through short-term and long-term goals to come up with fast go-to-market products, while planning ahead for productization. • Up‑level the org: lead architecture reviews, codify patterns, mentor Senior Engineers, and multiply impact through documentation, code reviews, and pairing. • Startup‑ready: flexible, comfortable with ambiguity and constant change; proactive about process, documentation, and reliability without over‑engineering. • Lead the collaboration and define how AI engineers work cross-functionally with software engineers, devops, product managers and designers, to conceptualize and shape innovative and impactful solutions. Provide mentorship to junior team members and cultivate a culture of collaboration and innovation. • Ship meaningful experiments: prototype data/ML capabilities, evaluate feasibility and ROI, and make pragmatic calls on productionalizing with an eye on operating costs and risk.

• Help design, build, and ship GenAI features — RAG pipelines, LLM-powered applications, and conversational interfaces — across our products. • Take ambiguous problems, break them into approaches, prototype quickly, and iterate based on what you learn. • Work with LLM APIs and AWS services (Bedrock, Lambda) to wire up prototypes, pipelines, and integrations. • Build and consume APIs to connect models to data, databases, and backend systems. • Test, evaluate, and debug AI behavior — prompts, retrieval quality, edge cases — to make sure things actually work. • Document what you build and share what you learn with the team. • Keep up with a fast-moving field and bring ideas back to us.