AI Engineer

We are seeking an exceptional AI Engineer to join our growing team and take a leading role in building and evolving our internal AI-powered agent platform used across the organization. In this role, you will design, build, and improve AI-powered applications that integrate large language models (LLMs) with internal tools, SQL databases, advertising APIs (Google Ads, Meta), and stateful code execution environments. You will play a critical role in improving reliability, context orchestration, evaluation maturity, and expanding Rai into document and workflow automation use cases. Your work will directly impact 200-500 employees and potentially clients, making AI a core productivity multiplier across the organization. Responsibilities include but are not limited to: LLM Application Development Design, build, and maintain AI-powered applications leveraging LLM APIs, tool calling, and structured outputs. Agent & Tool Orchestration Develop and improve agent architectures that integrate tools such as SQL execution, Python code execution, and marketing platform APIs through MCP-style integrations. Context & Memory Management Design and refine multi-turn context handling, session memory strategies, and prompt structures to improve response reliability and reduce hallucinations. Reliability & Guardrails Implement safeguards for tool execution, SQL queries, and code execution. Improve retry logic, structured validation, and hallucination mitigation strategies. Evaluation & Quality Assurance Contribute to building structured evaluation frameworks for LLM-powered systems, including multi-turn testing, regression testing, and task-based success metrics. Product Expansion Support expansion of Rai into document generation, tables, slide decks, and potential Google Workspace integrations. Collaboration Work closely with Machine Learning Engineers, Product Managers, and Full-Stack Engineers to ensure AI systems are robust, maintainable, and aligned with business goals. Continuous Innovation Stay current with advances in LLM systems, agent architectures, and applied AI tooling to continuously improve Rai's capabilities. Requirements Strong programming skills in Python with experience building production systems. Experience building applications powered by LLM APIs (OpenAI, Anthropic, Vertex AI, etc.). Deep understanding of: Context windows and token limits Multi-turn conversation behavior Tool/function calling Structured outputs (JSON schema) Prompt design and failure modes Experience integrating external APIs into production systems. Proficiency in SQL. Experience working with cloud platforms (GCP, AWS, or Azure). Strong problem-solving skills and ability to debug complex system behavior. Excellent communication and cross-functional collaboration skills. Strong Plus Experience designing evaluation frameworks for LLM-powered systems. Understanding of embeddings, vector search, and RAG architectures. Experience building agent or multi-agent workflows. Experience with stateful execution environments or sandboxed code execution. Experience with document automation (Google Docs, Slides, PDFs). Experience building internal developer tools or productivity platforms. TypeScript. Required knowledge of: Python SQL Cloud Platforms (GCP, AWS, Azure) LLMs / AI APIs Git / GitHub Nice to have: Data Warehouses (BigQuery, Snowflake, Redshift) Data Transformation (dbt) Semantic Layers (Cube, Looker, dbt Metrics) TypeScript Our interview process includes, but is not limited to the following: Excel and Typing Test We offer a competitive salary and benefits based on ability level, including: Unlimited vacation policy Monthly Phone Stipend Comprehensive Medical, Dental, and Vision insurance options 401(K) plan with matching Dog friendly office Hybrid work opportunity Professional Development Program Bonus Perk - Seamless allowance Total compensation based on education, experience, and skills level ($90,900-$254,100) Level 1 - Possesses essential capabilities $90,900-$123,540 Level 2 - Possesses developing capabilities $123,540-$156,180 Level 3 - Possesses notable capabilities. $156,180-$188,820 Level 4 - Possesses strong capabilities. $188,820-$221,460 Level 5 - Possesses advanced capabilities. $221,460-$254,100 About WITHIN WITHIN is the world's first Performance Branding company, partnering with some of the biggest brands in the world to drive business growth through innovative marketing strategies. Our integrated operating model collapses the traditional marketing silos between creative and media, performance and brand, and across media channels. With a full suite of offerings including media, creative, SEO, Lifecycle, Retail Media, Affiliate and Influencer, we're able to work with our brand partners in an integrated fashion, allowing us to align marketing strategies back to core business objectives. Client teams at WITHIN are trained on how to always act as a trusted business partner, acting as a fiduciary to client needs above our own. Teams at WITHIN have the ability to work with iconic brands such as The North Face, Timberland, Ben and Jerry's and Jose Cuervo. Everyone at WITHIN wants to grow and be challenged. It's a collaborative place made up of small, closely knit and versatile teams that are fast and adaptive to solve problems and build systems. Check out some of our work! We weave AI into everything we do , using the latest tech across all teams to innovate, work smarter, and make better decisions. Whether it's in creative, operations, or anything else, AI helps us level up and do things at a whole new scale. We expect our people to use AI in their daily work, fully embracing it as a critical tool to help us succeed. Join Our Network! Stay connected with us and be the first to know about new opportunities, industry insights, and updates. Follow us on: LinkedIn WhatsApp Community I nstagram Tik Tok Locations New York City: 43-01 22nd St, Suite 602, Queens, NY 11101, United States Bogota: WeWork Av. Carrera 19 #100-45 Usaquen, Piso (Floor) 10, Bogota, Distrito Capital de Bogota 110111, Colombia Mexico City: Av. Insurgentes Sur 1082, Piso (Floor) 2, Oficina 2008, Ciudad de Mexico, CDMX 03100, Mexico AI-Assisted Screening Notice As part of our initial application review process, we may use an AI-assisted tool to help compare skills and job titles from your resume with the requirements of the role. This tool evaluates information based on contextual relevance and is used only to support our manual review process. It is not used to make hiring decisions. If you are a resident of New York City and would like to request an alternative evaluation process or a reasonable accommodation, please contact us at legal@within.co. Create a Job Alert Interested in building your career at WITHIN? Get future opportunities sent straight to your email. Create alert Apply for this job * indicates a required field Autofill with MyGreenhouse First Name* Last Name* Email* Phone Country* Phone* Resume/CV* AttachAttach Dropbox Google Drive Enter manuallyEnter manually Accepted file types: pdf, doc, docx, txt, rtf * * * What is your personal email?* What is your total yearly salary expectation, inclusive of any merit based bonuses, on-target earnings, commissions, etc.? ($XXX,XXX USD)* Are you currently authorized to work lawfully in the United States, and will you require future sponsorship?* Select... Did someone refer you? If yes, please provide name.* How did you find us?* Where are you located? (City, Country)* Please provide a link to your LinkedIn Profile.* Are you open to a hybrid working environment, includes both in-office and remote work?* Select... Please provide links to your relevant publicly accessible Facebook, Instagram and/or Twitter accounts (if any) and any blogs you maintain. Please separate each link with a comma.* As a digital marketing company, we place importance on a professional digital presence and consider it in our evaluation of all candidates. We want to let you know that our office is dog-friendly, with dogs present in the office regularly. Are you comfortable working in an environment where dogs are present?* Select... Are you comfortable working in an environment where AI usage is a requirement, and is integrated into every aspect of the work we do? * Select... Do you have a professional or personal connection to a current client, partner, or brand we work with?* Select... Have you personally built and deployed a machine learning product that is currently in production? * Select... Was the ML product you worked on successful in achieving measurable outcomes? * Select... Did you take full ownership of any part of the AI or ML pipeline? * Select... Has the ML product you built been in production for more than six months without major performance issues? * Select... Did you oversee the ML or AI product after deployment, including monitoring, retraining, and maintenance? * Select... Have you solved real-world ML problems involving challenges such as data quality, model generalization, or scaling? * Select... Which best describes the most complex ML or AI product you've personally worked on? * Select... Have you worked at a company or department known for strong machine learning or data science capabilities? * Select... If you indicated that you have a connection to one of our current clients, partners, or brands, please provide the individual's name, the client/partner/brand, and describe your relationship. Voluntary Self-Identification For government reporting purposes, we ask candidates to respond to the below self-identification survey. Completion of the form is entirely voluntary. Whatever your decision, it will not be considered in the hiring process or thereafter. Any information that you do provide will be recorded and maintained in a confidential file. As set forth in WITHIN's Equal Employment Opportunity policy, we do not discriminate on the basis of any protected group status under any applicable law. Gender Select... Are you Hispanic/Latino? Select... Race & Ethnicity Definitions If you believe you belong to any of the categories of protected veterans listed below, please indicate by making the appropriate selection. As a government contractor subject to the Vietnam Era Veterans Readjustment Assistance Act (VEVRAA), we request this information in order to measure the effectiveness of the outreach and positive recruitment efforts we undertake pursuant to VEVRAA. Classification of protected categories is as follows: A "disabled veteran" is one of the following: a veteran of the U.S. military, ground, naval or air service who is entitled to compensation (or who but for the receipt of military retired pay would be entitled to compensation) under laws administered by the Secretary of Veterans Affairs; or a person who was discharged or released from active duty because of a service-connected disability. A "recently separated veteran" means any veteran during the three-year period beginning on the date of such veteran's discharge or release from active duty in the U.S. military, ground, naval, or air service. An "active duty wartime or campaign badge veteran" means a veteran who served on active duty in the U.S. military, ground, naval or air service during a war, or in a campaign or expedition for which a campaign badge has been authorized under the laws administered by the Department of Defense. An "Armed forces service medal veteran" means a veteran who, while serving on active duty in the U.S. military, ground, naval or air service, participated in a United States military operation for which an Armed Forces service medal was awarded pursuant to Executive Order 12985. Veteran Status Select... Voluntary Self-Identification of Disability Form CC-305 Page 1 of 1 OMB Control Number 1250-0005 Expires 04/30/2026 Why are you being asked to complete this form? We are a federal contractor or subcontractor. The law requires us to provide equal employment opportunity to qualified people with disabilities. We have a goal of having at least 7% of our workers as people with disabilities. The law says we must measure our progress towards this goal. To do this, we must ask applicants and employees if they have a disability or have ever had one. People can become disabled, so we need to ask this question at least every five years. Completing this form is voluntary, and we hope that you will choose to do so. Your answer is confidential. No one who makes hiring decisions will see it. Your decision to complete the form and your answer will not harm you in any way. If you want to learn more about the law or this form, visit the U.S. Department of Labor's Office of Federal Contract Compliance Programs (OFCCP) website at www.dol.gov/ofccp. How do you know if you have a disability? A disability is a condition that substantially limits one or more of your "major life activities." If you have or have ever had such a condition, you are a person with a disability. Disabilities include, but are not limited to: Alcohol or other substance use disorder (not currently using drugs illegally) Autoimmune disorder, for example, lupus, fibromyalgia, rheumatoid arthritis, HIV/AIDS Blind or low vision Cancer (past or present) Cardiovascular or heart disease Celiac disease Cerebral palsy Deaf or serious difficulty hearing Diabetes Disfigurement, for example, disfigurement caused by burns, wounds, accidents, or congenital disorders Epilepsy or other seizure disorder Gastrointestinal disorders, for example, Crohn's Disease, irritable bowel syndrome Intellectual or developmental disability Mental health conditions, for example, depression, bipolar disorder, anxiety disorder, schizophrenia, PTSD Missing limbs or partially missing limbs Mobility impairment, benefiting from the use of a wheelchair, scooter, walker, leg brace(s) and/or other supports Nervous system condition, for example, migraine headaches, Parkinson's disease, multiple sclerosis (MS) Neurodivergence, for example, attention-deficit/hyperactivity disorder (ADHD), autism spectrum disorder, dyslexia, dyspraxia, other learning disabilities Partial or complete paralysis (any cause) Pulmonary or respiratory conditions, for example, tuberculosis, asthma, emphysema Short stature (dwarfism) Traumatic brain injury Disability Status Select... PUBLIC BURDEN STATEMENT: According to the Paperwork Reduction Act of 1995 no persons are required to respond to a collection of information unless such collection displays a valid OMB control number. This survey should take about 5 minutes to complete. Submit application Powered by Greenhouse