Y Combinator Member of Technical Staff, AI
Summary
Designs and ships LLM-powered applications and agent systems end to end at WITHIN, a performance branding/marketing company — owning the full product lifecycle from problem definition through launch, scaling, and maintenance. Core stack: Python, LLM APIs (OpenAI/Anthropic/Vertex AI), agent workflows, evals, plus TypeScript/React and cloud platforms.
About the Role
As a Member of Technical Staff focused on AI, you will design applied AI systems and build the products around them across frontend, backend, and data. End-to-end product ownership is central to the role. You will define the problem, decide what to build, ship it, evaluate the result, and maintain it after launch.
Most of your technical work will involve LLM-powered applications, agent systems, and the evaluation and reliability systems required to run them in production.
The role is full lifecycle
- Find product-market fit. Start with a small version, test it with users, and decide whether to continue, change direction, or stop.
- Improve what works. Once a product proves useful, test changes and invest in the versions that perform best.
- Expand and scale. Grow adoption across WITHIN and with clients, and make the system reliable under increased use.
- Maintain it. Monitor performance, resolve problems, and continue improving the product.
You will set direction with business partners. They provide domain context and user needs; you decide how to scope, sequence, and develop the product.
How we work
- AI-native. We use coding assistants and agent workflows throughout development. Engineers are responsible for testing and reviewing the resulting work.
- Bias to ship. Engineers work directly with business teams, make product and technical decisions, and release work in small increments.
- Fast feedback loops, evidence over vibes. We observe how products perform and use feedback and product data to decide what to build next.
What we’re looking for
How you operate matters more than any specific technology:
- You have owned products end to end, from an ambiguous initial problem through launch and ongoing operation.
- You can decide what to test first, define success, and change course when results do not support the current plan.
- AI tools are already part of how you scope, build, test, and maintain software.
- You can choose between model behavior, deterministic software, and human review based on the problem.
- You work independently, communicate tradeoffs, and keep the people involved informed.
Technical foundation:
- Strong Python skills and experience building production systems.
- Experience building production applications with LLM APIs such as OpenAI, Anthropic, or Vertex AI.
- Experience building agent workflows that use tools, call external systems, maintain state, and handle multi-step tasks.
- Experience designing evaluations for LLM-powered systems, including test cases, quality measures, regression testing, and review of production failures.
- Understanding of context management, token limits, multi-turn conversations, tool calling, structured outputs, prompt design, and common failure modes.
- Experience integrating external APIs and working with SQL.
- Experience tracing and debugging behavior across model calls, application code, tools, and external systems.
- Experience with GCP, AWS, or Azure.
- Ability to build the product around the AI components, including frontend, backend, and data. Experience with TypeScript, React, and backend services is a plus.
- Ability to explain technical tradeoffs and work directly with business teams.
Strong pluses
-
- Multi-agent architectures.
- Embeddings, vector search, and retrieval-augmented generation.
- Stateful or sandboxed code execution environments.
- Human review and approval workflows.
- Observability, model routing, latency management, and cost control for AI systems.
- Document automation (Google Docs, Slides, PDFs).
- Building internal developer tools or productivity platforms.
- Data warehouses (BigQuery, Snowflake, Databricks), data transformation (dbt), semantic layers (Cube, Looker, dbt Metrics).
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:
- WhatsApp Community
- Tik Tok
Locations
- New York City: 43-01 22nd St, Suite 602, Queens, NY 11101, United States
- Bogotá: WeWork Av. Carrera 19 #100-45 Usaquén, Piso (Floor) 10, Bogotá, Distrito Capital de Bogotá 110111, Colombia
- Mexico City: Av. Insurgentes Sur 1082, Piso (Floor) 2, Oficina 2008, Ciudad de México, CDMX 03100, México
Skills
As published by greenhouse · 22 questions · 1 written answer
Basics
First Name, Last Name, Email, Phone, Resume/CV
Short answers (8)
- 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)
- 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.
- 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. optional
- 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. optional
Pick from a list (13)
- Are you currently authorized to work lawfully in the United States, and will you require future sponsorship?
- Are you open to a hybrid working environment, includes both in-office and remote work?
- 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?
- Are you comfortable working in an environment where AI usage is a requirement, and is integrated into every aspect of the work we do?
- Do you have a professional or personal connection to a current client, partner, or brand we work with?
- Have you personally built and deployed a machine learning product that is currently in production?
- Was the ML product you worked on successful in achieving measurable outcomes?
- Did you take full ownership of any part of the AI or ML pipeline?
- Has the ML product you built been in production for more than six months without major performance issues?
- Did you oversee the ML or AI product after deployment, including monitoring, retraining, and maintenance?
- Have you solved real-world ML problems involving challenges such as data quality, model generalization, or scaling?
- Which best describes the most complex ML or AI product you’ve personally worked on?
- Have you worked at a company or department known for strong machine learning or data science capabilities?
Written answers (1)
- 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. optional