Technical AI Architect

We are looking for a senior engineer with 10+ years of experience into own AI systems in production and set the technical direction for our Generative AI work. You will architect and optimize RAG pipelines, agentic workflows, and enterprise AI applications; establish evaluation and reliability practices; drive latency, cost, and observability improvements; and mentor other engineers. You will partner with product and business stakeholders to shape the roadmap and deliver scalable, secure, enterprise-ready AI solutions. This role is for someone who has taken AI systems to production and is ready to lead.

Technical Skills:

• Proficiency in Python, including asynchronous programming, concurrency, testing, packaging, and performance optimization.
• Extensive experience designing, developing, deploying, and supporting AI-powered applications using Large Language Models (LLMs).
• Experience integrating multiple AI provider APIs such as OpenAI, Anthropic, Gemini, or similar LLM platforms, including model selection, fallback strategies, and provider abstraction.
• Strong experience implementing structured outputs, function/tool calling, streaming responses, context management, and memory strategies for production AI systems.
• Experience designing and optimizing Retrieval-Augmented Generation (RAG) pipelines, including chunking strategies, embedding models, vector database selection, semantic search, reranking, and retrieval quality optimization.
• Strong understanding of agentic AI workflows, planning, tool integration, multi-agent systems, and business process automation.
• Experience designing AI evaluation strategies using prompt evaluation, groundedness assessment, hallucination reduction, regression testing, and response quality measurement.
• Strong understanding of machine learning, Natural Language Processing (NLP), model evaluation, and practical data engineering concepts.
• Experience working with large-scale structured and unstructured enterprise datasets, document intelligence, and knowledge management systems.
• Experience designing scalable backend architectures, REST APIs, microservices, and distributed AI applications.
• Strong experience with databases such as MongoDB, PostgreSQL, Elasticsearch, vector databases, or similar technologies, including performance tuning and indexing strategies.
• Experience with Git, collaborative software development workflows.
• Knowledge of AI application observability, latency optimization, token optimization, cost optimization, monitoring, and production reliability.
• Understanding of AI security concepts, including prompt injection prevention, secure AI application development, responsible AI practices, and secure handling of enterprise data.
• Experience providing technical leadership through architecture reviews, mentoring, code reviews, and engineering best practices.

Key Responsibilities:

• Design, develop, and own scalable AI-powered applications deployed in production environments.
• Architect and optimize Retrieval-Augmented Generation (RAG) pipelines, document intelligence platforms, and enterprise AI solutions.
• Design and implement advanced agentic AI workflows for complex business process automation and multi-step reasoning.
• Define technical strategies for prompt engineering, structured outputs, context management, and tool integration across AI applications.
• Establish evaluation frameworks to continuously improve groundedness, response quality, hallucination reduction, and overall AI system reliability.
• Optimize AI applications for latency, scalability, observability, token utilization, operational cost, and production performance.
• Design scalable backend architectures, REST APIs, microservices, and data pipelines supporting enterprise AI applications.
• Mentor engineers through technical guidance, architecture discussions, design reviews, and code reviews.
• Collaborate with engineering, product, and business stakeholders to define technical roadmaps and deliver enterprise AI solutions.
• Lead production troubleshooting, reliability improvements, and continuous optimization of AI systems.
• Document solution architectures, technical designs, implementation guidelines, and operational best practices to support long-term maintainability.

Qualifications:

• Education: Bachelor's degree in Computer Science, Data Science, Artificial Intelligence, or a related field.
• Experience: 3+ years of professional software/backend engineering experience, including hands-on production Generative AI work.

Soft Skills:

• Technical leadership sets direction and brings others along, without needing formal authority.
• Mentors and grows engineers through guidance, design discussions, and reviews.
• Sound judgment and decision-making under ambiguity and competing constraints (quality, cost, speed).
• Communicates effectively with both technical teams and non-technical business stakeholders.
• Takes ownership of outcomes, including production incidents and their resolution.
• Drives clarity, turns vague problems into concrete and well-scoped technical plans.
• Champions engineering standards, documentation, and long-term maintainability.
• Stays current with a fast-moving field and helps the team adopt what matters.

Skills

AI, LLM, Machine Learning, NLP, Python, RAG, Retrieval-Augmented Generation