• Build and scale the agent runtime at Newfront • Design and own RAG and document understanding pipelines for complex insurance artifacts • Build the connector framework that lets AI agents and pipelines reach into the systems brokers actually use • Establish the evaluation and observability backbone for AI at Newfront • Own model routing and the model gateway • Stand up and operate on-premise model hosting • Ship AI product features end-to-end on top of the platform • Mentor engineers on production AI systems, review designs, and help establish best practices for building reliable AI in financial services • Partner with security, privacy, and compliance to bake controls into the platform

• Design, build, and iterate on AI Assistants integrated with enterprise tools including Jira, Slack, and internal data sources • Develop and maintain prompt engineering frameworks, evaluation pipelines, and feedback loops to continuously improve assistant quality and reliability • Build and maintain APIs, backend services, and integrations that connect AI capabilities to the tools teams already use • Collaborate with AI Ops, security, and platform engineering teams to ensure systems are production-grade, secure, and observable • Contribute to a repeatable framework for building new AI Assistants as the program expands • Evaluate new models, tools, and libraries and make informed recommendations on when and how to adopt them • Identify and mitigate risks related to AI outputs, data handling, and responsible use • Contribute to technical documentation, runbooks, and onboarding materials that help the team scale what gets built

Role Description We are looking for a passionate and skilled AI engineer who is responsible for designing and delivering complex generative AI solutions. This role requires the ability to work autonomously on challenging technical problems, provide mentorship to junior engineers, and champion engineering best practices. - Design, build and deploy GenAI applications using techniques such as RAG, Agents, Multi Agent Systems, etc., taking ideas from prototype to production. - Work with both AI/ML engineers and software engineers to deliver reliable, scalable systems. - Own key features or components, ensuring they are well-structured, efficient, and easy to maintain. - Make technical decisions and contribute to system design with attention to performance, cost, and reliability. - Collaborate with product managers, designers, and data scientists to turn business needs into practical solutions. - Share knowledge and mentor junior team members, helping them grow their technical skills. - Review code and provide clear, constructive feedback to peers. - Understand deployment options and trade-offs across different cloud providers such as AWS, Azure, Google Cloud, etc. - Understand optimization techniques to improve accuracy, performance, and cost for GenAI applications. Qualifications - Strong software engineering fundamentals, including Python, CI/CD, testing, version control, and clean code practices. - Solid grasp of software design principles and ability to design and implement AI-powered components or workflows. - Experience with at least one GenAI framework (e.g., LangChain, LlamaIndex, Semantic Kernel) and one agentic framework (e.g., PydanticAI, LangGraph, AutoGen2). - Hands-on experience building and optimizing Retrieval-Augmented Generation (RAG) pipelines with vector databases (e.g., FAISS, Pinecone, Weaviate). - Familiarity with deploying AI solutions on major cloud platforms (AWS, Azure, or GCP), with basic use of containers (Docker) and CI/CD pipelines. - Experience using LLMOps and observability tools (e.g., Langfuse, PromptLayer, OpenTelemetry) in production. - Exposure to fine-tuning and use of ML/NLP frameworks such as PyTorch or Hugging Face Transformers. Requirements - Ability to independently solve complex, ambiguous technical problems. - Willingness and ability to guide and mentor junior engineers, sharing knowledge and best practices. - Strong collaborative skills, working effectively with diverse, cross-functional teams. - Thrives in a dynamic and fast-paced environment, demonstrating resilience in the face of challenges. Benefits - There is no one-size-fits-all career path at Thoughtworks: however you want to develop your career is entirely up to you. - Your career is supported by interactive tools, numerous development programs, and teammates who want to help you grow. - We see value in helping each other be our best and that extends to empowering our employees in their career journeys. Company Description Thoughtworks is a dynamic and inclusive community of bright and supportive colleagues who are revolutionizing tech. As a leading technology consultancy, we’re pushing boundaries through our purposeful and impactful work. For 30+ years, we’ve delivered extraordinary impact together with our clients by helping them solve complex business problems with technology as the differentiator. Bring your brilliant expertise and commitment for continuous learning to Thoughtworks. Together, let’s be extraordinary.

• Design and develop new AI-powered applications with browser-based and conversational interfaces to support modern HR functions. • Build and maintain shared infrastructure that supports a growing portfolio of agentic AI applications, including AWS EC2 servers, Airflow workflows, CI/CD pipelines, and Snowflake integrations. • Integrate LLM APIs into enterprise applications and HR workflows, delivering tangible AI-powered features. • Partner with HR stakeholders to translate needs into AI solutions that improve the employee experience. • Collaborate with data scientists to deploy and manage AI systems, ensuring scalability, reliability, and efficiency. • Experiment with and implement agentic frameworks to extend future AI capabilities.