proSapient logo
proSapient

Connecting you to industry professionals around the world

Search & AI Retrieval Lead

AI EngineerMachine Learning EngineerFull TimeRemoteLeadTeam 201-500H1B No SponsorCompany SiteLinkedIn

Location

United Kingdom

Posted

64 days ago

Salary

0

Seniority

Lead

English

Job Description

Search & AI Retrieval Lead

proSapient

Role Description As our Search & AI Retrieval Lead , you’ll define how structured data, semantic understanding, and intelligent systems come together to power discovery across our platform. From knowledge graphs to LLM-driven enrichment and recommendation systems, you’ll be at the forefront of building something genuinely cutting-edge — with real impact on how our users experience and navigate information. The key duties of this role will include: - Search Architecture Strategy: - Evaluate and define the future search stack (technology selection is part of the role). - Design a scalable, cloud-native search architecture from first principles. - Decide between and combine approaches such as: - Keyword search - Vector search - Hybrid retrieval - Graph-based retrieval - LLM re-ranking - Design indexing, data modeling, and ranking strategies. - Define measurable relevance and quality frameworks. - Knowledge Graph & Intelligent Retrieval: - Design and implement a Knowledge Graph architecture modeling entities and relationships. - Define graph schema, linking strategies, and enrichment workflows. - Combine graph-based signals with semantic search and ranking models. - Build extraction pipelines on top of frontier models (OpenAI, Gemini). - Develop modern recommendation systems leveraging structured + unstructured data. - Data & Cloud Infrastructure (GCP-first): - Architect retrieval pipelines on Google Cloud Platform (GCP). - Design data pipelines and feature stores using BigQuery or alternative analytical systems. - Ensure scalability, observability, and cost efficiency. - Build production-grade systems, not experiments. Qualifications - 5+ years building and scaling production search or retrieval systems. - Strong experience designing search architectures, not just operating them. - Experience evaluating and selecting search technologies. - Experience with semantic search and embeddings-based retrieval. - Experience building pipelines on top of frontier LLMs (OpenAI, Gemini). - Strong Python skills. - Experience leading technical initiatives in mid-sized teams. - Experience working with cloud-native systems (preferably GCP). Benefits - Tenure Gifts - Vouchers, extra holiday and sabbaticals for each year of employment. - Health insurance through Vitality. - Employee Assistance Programme - Access to a health and wellbeing service that offers personalised advice and support from specialist teams. - Enhanced Maternity & Paternity pay. - Annual Leave - 25 days + bank holidays which includes a week's closure over the Christmas period to fully reset. - MyMindPal app - Online support for mental fitness that helps people to stress less and enjoy life more. - Corporate Events - From quarterly gatherings to our annual winter & summer parties, we love to celebrate, collaborate and have fun together! Company Description Consulting and private equity firms come to proSapient when they need to discover knowledge to help them make great decisions and succeed in their goals. It is our mission to support them in their discovery of knowledge. We help our clients find industry experts who can provide their knowledge via interview or survey: we curate this knowledge in a market-leading software platform; and we help clients surface knowledge they already have through expansive knowledge management. We are committed to building an inclusive workplace – did you know that marginalized groups are less likely to apply to jobs unless they meet every requirement listed? If you are interested in the above role, but don’t necessarily tick every box, we encourage you to apply anyway – this role could still be a great match!

Job Requirements

  • 5+ years building and scaling production search or retrieval systems.
  • Strong experience designing search architectures, not just operating them.
  • Experience evaluating and selecting search technologies.
  • Experience with semantic search and embeddings-based retrieval.
  • Experience building pipelines on top of frontier LLMs (OpenAI, Gemini).
  • Strong Python skills.
  • Experience leading technical initiatives in mid-sized teams.
  • Experience working with cloud-native systems (preferably GCP).

Benefits

  • Tenure Gifts - Vouchers, extra holiday and sabbaticals for each year of employment.
  • Health insurance through Vitality
  • Employee Assistance Programme - Access to a health and wellbeing service that offers personalised advice and support from specialist teams.
  • Enhanced Maternity & Paternity pay.
  • Annual Leave - 25 days + bank holidays which includes a week's closure over the Christmas period to fully reset.
  • MyMindPal app - Online support for mental fitness that helps people to stress less and enjoy life more
  • Corporate Events - From quarterly gatherings to our annual winter & Summer parties, we love to celebrate, collaborate and have fun together!
  • We are committed to building an inclusive workplace – did you know that marginalized groups are less likely to apply to jobs unless they meet every requirement listed? If you are interested in the above role, but don’t necessarily tick every box, we encourage you to apply anyway – this role could still be a great match! Take a look at our diversity statement here.

Related Job Pages

More AI Engineer Jobs

Booksy logo

AI-Native Software Engineer

Booksy

Appointments made easy.

AI Engineer64 days ago
Full TimeRemoteTeam 51-200Since 2013H1B No Sponsor

Role Description As an AI-Native Engineer reporting to an Engineering Manager in our Product & Tech team, your purpose will be to help us redefine the engineering craft by integrating AI in our development lifecycle. We’re looking for someone who doesn't just use AI, but wants to reimagine how software is built from the ground up. Specifically, you will: - Build & Deploy: Make use of the latest AI tools for building and shipping our next product hit. - Innovate: Work on bold, AI-first product features from ideation to launch, solving real-world problems for our users. - Collaborate: Partner with experienced engineers, product managers, and designers to bring new ideas to life. - Learn & Grow: Be a key contributor in an environment that values continuous learning, curiosity, and creative problem-solving. Qualifications - Between zero and one year of commercial experience in Software Engineering or another role in the tech area (regardless of your overall professional experience). - An innate curiosity and a "builder" mentality. You are not just a user of AI, but a pioneer who will help us discover new ways to achieve higher goals. - Initial practical experience with AI Tools, including AI-assisted development tools such as Claude Code, Gemini, and Cursor, and initial comprehension of agentic workflows and concepts like MCP. - Familiarity with one or more modern programming languages (Python, JavaScript). - A portfolio or user case study of a relevant project from an open-source contribution or home project. - Fluency in English. Benefits - Private medical care from Allianz health (subsidized by Booksy). - Life insurance from Uniqua (covered by Booksy, employee cost- 1 PLN). - Multisport card (voluntary and unsubsidized, diverse packages to choose from). - Online consultations with Psychologist Booksy (fully subsidized by the company). - Access to English online language training (Speexx). - Employee wellbeing platform: Worksmile (employees can redeem shopping vouchers). - Additional life Insurance from PZU (unsubsidized, voluntary). - Work in a welcoming team that is always ready to help. - Opportunity to develop in an international environment - we have teams in 6 countries.

Poland
Job Closed
Scratch Financial logo

AI Engineer

Scratch Financial

Scratch Financial is the world's simplest patient financing solution.

AI Engineer64 days ago
Full TimeRemoteTeam 11-50Since 1912H1B Sponsor

Company Description NBCUniversal is one of the world's leading media and entertainment companies. We create world-class content, which we distribute across our portfolio of film, television, and streaming, and bring to life through our global theme park destinations, consumer products, and experiences. We own and operate leading entertainment and news brands, including NBC, NBC News, NBC Sports, Telemundo, NBC Local Stations, Bravo, and Peacock, our premium ad-supported streaming service. We produce and distribute premier filmed entertainment and programming through our powerhouse film and television studios, including Universal Pictures, DreamWorks Animation, and Focus Features, and the four global television studios under the Universal Studio Group banner, and operate industry-leading theme parks and experiences around the world through Universal Destinations & Experiences, including Universal Orlando Resort, home to Universal Epic Universe, and Universal Studios Hollywood. NBCUniversal is a subsidiary of Comcast Corporation. Visit www.nbcuniversal.com for more information. Our impact is rooted in improving the communities where our employees, customers, and audiences live and work. We have a rich tradition of giving back and ensuring our employees have the opportunity to serve their communities. We champion an inclusive culture and strive to attract and develop a talented workforce to create and deliver a wide range of content reflecting our world. Job Description The forward-deployed AI Engineer designs, builds, and ships AI-powered solutions, including agentic systems, that transform workflows and unlock new capabilities across NBCUniversal News Group. This role is deeply technical, highly collaborative, and execution-focused, with success measured by production adoption and measurable operational impact. This individual works end-to-end from discovery and prototyping through deployment and iteration, combining LLMs, retrieval, data integration, and orchestration frameworks to deliver reliable solutions in production. This is not a backend-only role; the engineer will build across services, integrations, and user-facing experiences as needed. Engineers will work closely with editorial, product, data, and technology teams to co-create solutions in a fast-moving, real-time business environment where speed and timely delivery are critical. Key Responsibilities: Design, Build, and Ship AI + Agentic Solutions - Architect and implement end-to-end AI applications from concept to production, including agentic workflows. - Build systems using LLMs and multimodal models, retrieval and vector databases, and orchestration frameworks (e.g., LangChain/LangGraph, Google ADK), integrated with internal tools and data. - Own the full lifecycle: discovery, prototyping, validation, deployment, monitoring, iteration, and support. Execute Fast in a High-Velocity Environment - Deliver solutions on accelerated timelines aligned to editorial and business urgency. - Prioritize evidence-driven iteration over perfection; make clear tradeoffs across scope, speed, and quality. - Adapt quickly to changing requirements and real-world feedback, keeping stakeholders aligned. Hands-On Technical Execution - Write production-quality code and integrate APIs across internal platforms and external providers (e.g., Google, OpenAI, Databricks, AWS, Microsoft). - Make pragmatic architectural decisions balancing speed, scale, security, reliability, and cost. - Build reusable components, templates, and playbooks that accelerate future development and reduce friction for downstream teams. Apply the Right AI to the Right Problems - Evaluate model capabilities and select appropriate AI tools based on workflow needs, risk profile, and operational constraints. - Combine services across selected providers into cohesive, reliable systems with strong observability and clear failure modes. - Implement evaluation frameworks to measure quality, reliability, and impact, and to guide iteration. Responsible AI, Safety, and Governance - Design guardrails for agentic systems, including tool safety, permissioning, data handling, and human-in-the-loop review where needed. - Partner with Standards, Legal, Security, and GRC to ensure compliant data use, responsible deployment, and audit-ready practices. - Establish monitoring and incident response patterns to detect issues and maintain trust and reliability at scale. Collaborate Deeply Across Teams - Work directly with editorial, product, and business partners to shape solutions from requirements through rollout. - Collaborate with our Data team on data quality, retrieval strategies, evaluation design, and measurement. - Partner with the CTO and platform engineering organizations to harden solutions for production environments. - Communicate clearly with technical and non-technical audiences, translating complexity into decisions and action. Stay Ahead of the Market - Track new model releases, vendor updates, and emerging patterns in agentic AI. - Run targeted experiments with new capabilities and share timely recommendations that influence roadmaps and standards. Leverage AI in the Role - Use AI coding agents and copilots to accelerate development, debugging, refactoring, test generation, and documentation. - Apply AI to speed analysis, coordination, and knowledge capture while maintaining security, quality, and compliance. Qualifications - 4+ years of professional software engineering experience (or equivalent). - Proven experience shipping production systems (not just prototypes). - Strong coding skills in Python and/or TypeScript/JavaScript; comfortable with APIs and system integration. - Hands-on experience with LLM-powered applications (agentic patterns, prompting, orchestration/agents, evaluation, deployment considerations). - Demonstrated ability to effectively use AI coding agents (e.g., agentic IDE tools) to speed delivery while ensuring correctness, testing, maintainability, and secure coding practices. - Strong communication skills with technical and non-technical stakeholders. Desired Characteristics: - Experience with LangChain and/or LangGraph for orchestrating agentic workflows (routing, state machines, multi-agent patterns, tool execution). - Experience with Google ADK (or comparable agent development kits) for building and operationalizing agents. - Familiarity with cloud infrastructure (AWS/GCP/Azure), observability, and production operations. - Exposure to model evaluation concepts and responsible AI practices. Additional Requirements: - Hybrid: This position currently has a hybrid schedule, which requires contributing from the office a minimum of four days per week. The Company reserves the right to change in-office requirements at any time. This position is eligible for company sponsored benefits, including medical, dental and vision insurance, 401(k), paid leave, tuition reimbursement, and a variety of other discounts and perks. Learn more about the benefits offered by NBCUniversal by visiting the Benefits page of the Careers website. Salary range: $110,000-$120,000 Additional Information As part of our selection process, external candidates may be required to attend an in-person interview with an NBCUniversal employee at one of our locations prior to a hiring decision. NBCUniversal's policy is to provide equal employment opportunities to all applicants and employees without regard to race, color, religion, creed, gender, gender identity or expression, age, national origin or ancestry, citizenship, disability, sexual orientation, marital status, pregnancy, veteran status, membership in the uniformed services, genetic information, or any other basis protected by applicable law. If you are a qualified individual with a disability or a disabled veteran and require support throughout the application and/or recruitment process as a result of your disability, you have the right to request a reasonable accommodation. You can submit your request to AccessibilitySupport@nbcuni.com.

New York
$110K - $120K / year
Job Closed
Full TimeRemoteTeam 51-200H1B No Sponsor

• Develop solutions to integrate and optimize language models within the botario platform • Stay informed about current developments in AI research • Monitor trends and advancements in NLP and AI research • Apply LLMs in production for customers in combination with the botario platform • Experiment with new models and architectures • Evaluate LLMs with respect to response quality, latency, cost, and other factors

Germany
Teamified logo

Product Engineer

Teamified

Empower Global Teams

AI Engineer64 days ago
Full TimeRemoteTeam 201-500Since 2021H1B No Sponsor

Role Description We are seeking a talented and experienced Senior AI Data Engineer to join our dynamic team. As a Senior AI Data Engineer, you will be responsible for designing, developing, and implementing AI solutions to enhance our products and services. You will work closely with our principal software engineer and platform software engineers to create cutting-edge AI models and algorithms. - Design and develop our Teamified AI data architecture & API using Python (Django Framework) and other relevant python libraries - Manage our RDBMs [SQL], NoSQL [MongoDb] and Vector [Pinecone] databases and conduct proper data governance & research - Collaborate with our leadership, product experts and software architect to integrate AI solutions into our Teamified Platform - Optimize AI augmentation models, context builders and prompt builders for performance, scalability, and efficiency. - Conduct research and stay up-to-date on the latest advancements in AI and data engineering. Qualifications - Bachelor's or Master's degree in Computer Science, Information Technology, or a related field. - 3+ years of experience in AI data engineering. - Proficiency in Python and Django Framework and other relevant tools and technologies. - Good-to-have skills: RAG Orchestration Pipelines, LangChain, Vector Databases, PineCone. - Strong problem-solving skills and attention to detail. - Excellent communication and teamwork skills. - Ability to work independently and collaboratively in a fast-paced environment. Requirements - Flexibility in work hours and location, with a focus on managing energy rather than time. Benefits - Access to online learning platforms and a budget for professional development - A collaborative, no-silos environment, encouraging learning and growth across teams - A dynamic social culture with team lunches, social events, and opportunities for creative input - Health insurance - Leave Benefits

Philippines