Senior AI Product Engineer

Citian; Washington (District of Columbia); On-site; USD 150,000 - 210,000; Full time

Benefits offered by this job

Medical, dental, and vision insurance

Generous PTO

401(k) company match and commuterbenef

On-site gym and free snacks

Job summary

Citian invites a product-minded software engineer to design, build, and ship AI-enabled capabilities that integrate with our existing software stack. You will work across product, design, data science, and customer success to validate where AI adds value and ensure production-ready quality from data access to deployment.

You will balance prompt-based techniques, tool usage, retrieval, and potential fine-tuning, maintaining traceability, security, and governance while delivering reliable features

Qualifications

• Bachelor's degree in Computer Science, Data Science, or a related field.
• 5+ years building production software with shipped LLM features.
• Ability to take an ambiguous product problem through technical discovery, implementation, evaluation and production delivery.
• Has designed and run evaluations for LLM output: test sets, correctness and grounding measures, regression gates, and catching wrong answers before customers do.
• Full-stack skills: Python or TypeScript back ends, SQL and relational databases (PostgreSQL), APIs, and enough front end to ship a feature end to end.
• Production practices: code review, CI/CD, testing, monitoring and cost tracking.
• Uses AI coding tools and agents effectively in daily engineering work, including implementation, testing and investigation, while independently validating their output.
• Clear written English and solid overlap with US Eastern hours

Responsibilities

• Work with product, design, Customer Success and data science to understand agency problems, and help find and validate where AI adds value and where it doesn't.
• Design, build and ship AI-enabled capabilities within our products, end to end, from data access to the application.
• Fit model-based features into our existing software and data architecture without building unnecessary AI infrastructure, and record the key design decisions.
• Design and maintain evaluations for AI features, including correctness, grounding, authorization, appropriate abstention and regression detection. Establish practical release criteria and use production feedback to improve quality.
• Make AI-generated results traceable to their underlying data, queries and assumptions.
• Enforce customer isolation and each user's own permissions, including when tools retrieve or query data, and guard against prompt injection.
• Own features in production: latency, cost, reliability, monitoring, failure modes and incident response.
• Choose the right technique for each problem (prompting, tool use, retrieval, text-to-SQL, fine-tuning or no AI at all), weighing accuracy, cost, speed and time to market.

Skills

Ambiguity handling

Cross-functional collaboration

Decision making

Code review & CI/CD

Independent validation

Education

Bachelor's degree in Computer Science, Data Science, or a related field

Tools

Python

TypeScript

SQL

PostgreSQL

APIs

Frontend basics

Job description

Citian is a fast growing, venture backed SaaS technology company based in Washington, DC. Our software solutions revolutionize how our transportation and infrastructure systems – roads, rail, transit, bicycle, pedestrian – operate.

Our tech solutions:

• Reduce traffic fatalities
• Enhance pedestrian accessibility
• Empower system operators to save time & money

You’ll work with some of the brightest minds in the software and transportation industries. Our engineers and data scientists apply the latest in emerging tech, Artificial Intelligence, and Machine Learning to build smarter, more advanced tools for our diverse client base. We work with clients across the United States, with global ambitions in the years ahead.

Who You Are:

You're a product-minded software engineer who turns customer problems into reliable AI-enabled capabilities. You've built and shipped production LLM features, and you know the difference between a convincing demo and a dependable product. You work across the stack, prototype quickly, validate both the value and the correctness of what you build, and turn the experiments that work into production software. You know when AI is the right approach and when conventional software is better. You're comfortable with ambiguous requirements and work with engineering, data science and customer-facing teams to find where AI creates real value for transportation agencies.

Expected Duties:

• Work with product, design, Customer Success and data science to understand agency problems, and help find and validate where AI adds value and where it doesn't.
• Design, build and ship AI-enabled capabilities within our products, end to end, from data access to the application.
• Fit model-based features into our existing software and data architecture without building unnecessary AI infrastructure, and record the key design decisions.
• Design and maintain evaluations for AI features, including correctness, grounding, authorization, appropriate abstention and regression detection. Establish practical release criteria and use production feedback to improve quality.
• Make AI-generated results traceable to their underlying data, queries and assumptions.
• Enforce customer isolation and each user's own permissions, including when tools retrieve or query data, and guard against prompt injection.
• Own features in production: latency, cost, reliability, monitoring, failure modes and incident response.
• Choose the right technique for each problem (prompting, tool use, retrieval, text-to-SQL, fine-tuning or no AI at all), weighing accuracy, cost, speed and time to market.

Required Skills & Experience:

• Bachelor's degree in Computer Science, Data Science, or a related field
• 5+ years building production software, including shipped LLM features used by customers
• Demonstrated ability to take an ambiguous product problem through technical discovery, implementation, evaluation and production delivery
• Has designed and run evaluations for LLM output: test sets, correctness and grounding measures, regression gates, and catching wrong answers before customers do
• Full-stack product skills: Python or TypeScript back ends, SQL and relational databases (PostgreSQL), APIs, and enough front end to ship a feature end to end
• Production practices: code review, CI/CD, testing, monitoring and cost tracking
• Uses AI coding tools and agents effectively in daily engineering work, including implementation, testing and investigation, while independently validating their output
• Clear written English and solid overlap with US Eastern hours

Preferred Qualifications:

• Snowflake, AWS (including Bedrock), or LLMs over analytical or structured data
• Geospatial, transportation, public-sector or other complex, high-stakes data
• Security and compliance work around customer data (multi-tenant isolation, authorization, audit, SOC 2)
• Has led a feature end to end across teams

Your Citian Advantage:

• Competitive salary and benefits package including medical, dental, and vision insurance and generous PTO.
• 401(k) company match and monthly commuter transportation benefit
• On-site gym and free snacks in the office
• High-growth potential and opportunities for advancement within a fast growing, venture-backed SaaS startup!

** Citian is an organization committed to diversity and inclusion to drive our business results and create a better future every day for our diverse employees, clients, partners, and communities. We believe a diverse workforce allows us to match our growth ambitions and drive inclusion across the business. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, age, national origin, or protected veteran status and will not be discriminated against on the basis of disability.

Equal Opportunity/Affirmative Action Employer Minorities/Females/Protected Veterans/Persons with Disabilities